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

    Neuronpedia

    INDEX
    Explanations

    key terms and concepts related to research outcomes and data reporting

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

    Questions or question-answer pairs

    np_acts-logits-general · gemini-2.0-flash

    port, prices, former, legs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ProgressHUD
    -0.53
    ValueStyle
    -0.49
     disponibilités
    -0.48
    ⓘ
    -0.47
     Whom
    -0.47
     Continuity
    -0.47
     esso
    -0.46
    RetentionPolicy
    -0.45
    SerializedName
    -0.45
    дивиду
    -0.44
    POSITIVE LOGITS
     still
    1.09
     very
    1.08
     not
    1.06
     quite
    1.01
     able
    1.01
     extremely
    0.98
     always
    0.91
     is
    0.87
     unable
    0.85
     a
    0.83
    Act Density 0.526%

    No Known Activations