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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to function and method definitions

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

    Code snippets using "self" or "this"

    np_acts-logits-general · gemini-2.0-flash

    constructor initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رب
    -0.31
    FR
    -0.30
     FR
    -0.28
    <eos>
    -0.27
    est
    -0.26
    **********/
    -0.26
     misschien
    -0.26
     spots
    -0.25
    **/
    -0.25
     поми
    -0.25
    POSITIVE LOGITS
    SharedDtor
    0.86
    Diweddarwch
    0.79
     beginnetje
    0.77
     initState
    0.74
    ſelf
    0.74
     ब्रेकडाउन
    0.72
    нгред
    0.71
     ſtate
    0.71
     invokingState
    0.70
    SharedCtor
    0.70
    Act Density 0.029%

    No Known Activations