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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to making decisions and taking steps in various contexts

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

    deciding what to do or say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zijne
    -0.59
     zoude
    -0.55
     säll
    -0.54
     jongen
    -0.51
     apparaat
    -0.51
     mijne
    -0.49
     ModelExpression
    -0.48
    曖昧さ回避
    -0.47
    indelijk
    -0.47
     vermogen
    -0.47
    POSITIVE LOGITS
    windowFixed
    0.46
     вікісторінку
    0.45
    ToLoad
    0.44
    ToRead
    0.44
    ագրություններ
    0.38
     kaz
    0.37
     Dancing
    0.37
     jar
    0.37
     Kauai
    0.37
     Tallinn
    0.35
    Act Density 0.031%

    No Known Activations