Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code segments or structures that define parameters or properties related to functions or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or program code

    np_acts-logits-general · gemini-2.0-flash

    text following 'Pres:'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     WaitForSeconds
    -0.79
    ########.
    -0.76
    IBarButtonItem
    -0.75
    kloped
    -0.71
    SBATCH
    -0.71
    basicConfig
    -0.69
     препратки
    -0.68
     كومونز
    -0.68
     endfor
    -0.67
    ỡng
    -0.66
    POSITIVE LOGITS
    <tbody>
    0.56
     nakalista
    0.52
    zino
    0.50
    \">\
    0.43
    ModelState
    0.41
    <thead>
    0.41
     Trot
    0.40
    ագրություններ
    0.39
    ولد
    0.39
     panik
    0.39
    Act Density 0.161%

    No Known Activations