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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or analytical concepts

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

    Tokens after hyphens or separators

    np_acts-logits-general · gemini-2.0-flash

    stochastic gradient, Jaworski

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.71
    <eos>
    -0.46
    -
    -0.45
    rm
    -0.43
    ox
    -0.41
     Dem
    -0.41
    ep
    -0.40
    Dem
    -0.40
    -0.40
    nu
    -0.40
    POSITIVE LOGITS
     surla
    1.01
    httphttps
    0.82
     snippetHide
    0.82
     Paglinawan
    0.81
     betweenstory
    0.81
    DockStyle
    0.80
     myſelf
    0.80
    󠁴
    0.79
     GenerationType
    0.78
     jsPsych
    0.76
    Act Density 0.025%
    No Known Activations