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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluations and optimization in various contexts

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

    processes and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.65
     AppCompatTheme
    -0.53
    criptors
    -0.50
     itemprop
    -0.49
    ThroughAttribute
    -0.49
    GOTREF
    -0.48
     ſch
    -0.48
    enment
    -0.47
     Infórmanos
    -0.47
    ⇑
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.41
    tagHelperRunner
    0.37
     palsu
    0.33
    yelidikan
    0.33
    ̍t
    0.32
    ">//
    0.31
     Grüsse
    0.31
     somewhere
    0.31
    UVWXYZ
    0.31
     विश्वसनीयता
    0.30
    Act Density 0.394%

    No Known Activations