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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation specific to statistical functions or models

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

    hat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.52
    LookAnd
    -0.50
     Punj
    -0.49
    umu
    -0.48
    curo
    -0.47
    点此举报
    -0.47
    poss
    -0.47
    bourn
    -0.45
     Argo
    -0.44
    \"");
    -0.44
    POSITIVE LOGITS
    hat
    2.73
    HAT
    2.13
    Hat
    2.13
     Hat
    2.06
     hat
    2.03
     HAT
    1.79
    hats
    1.62
     hats
    1.54
     Hats
    1.36
    Hats
    1.32
    Act Density 0.040%

    No Known Activations