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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating future actions or intentions

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

    future actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.63
     contextLoads
    -0.60
    RegressionTest
    -0.59
     Verſ
    -0.58
     <<<<<<<<<<<<<<
    -0.57
    󰀄
    -0.56
     NSCoder
    -0.55
    Portály
    -0.54
     barbati
    -0.53
    bigsqcup
    -0.53
    POSITIVE LOGITS
    OGND
    0.38
     ролях
    0.33
    ようで
    0.33
     hatta
    0.33
    为止
    0.31
     stort
    0.31
     incorporating
    0.31
     potentially
    0.31
    Sucesor
    0.30
    ($__
    0.30
    Act Density 0.020%

    No Known Activations