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

    Neuronpedia

    INDEX
    Explanations

    references to goals and setting

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

    setting goals and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handles
    -0.33
    करण
    -0.32
    rajz
    -0.31
    culously
    -0.30
     része
    -0.27
     flavor
    -0.27
    ⓘ
    -0.27
    Kjelder
    -0.27
    러나
    -0.27
     zape
    -0.26
    POSITIVE LOGITS
    новништво
    0.66
     setter
    0.62
    encodeWith
    0.60
     límites
    0.59
    LookAnd
    0.59
     Setting
    0.58
    Хьажоргаш
    0.58
    basicConfig
    0.58
    setting
    0.57
     invokingState
    0.57
    Act Density 0.033%

    No Known Activations