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

    Neuronpedia

    INDEX
    Explanations

    helm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    larla
    -0.06
    short
    -0.06
     걸
    -0.06
     answers
    -0.06
     Selling
    -0.06
    rbrace
    -0.06
    480
    -0.06
    _free
    -0.06
     frequent
    -0.06
     granny
    -0.06
    POSITIVE LOGITS
    .hibernate
    0.07
     Lima
    0.07
    ByExample
    0.07
    Swipe
    0.07
    orio
    0.07
    :absolute
    0.06
    UInt
    0.06
    bildung
    0.06
     милли
    0.06
     ΔΗΜ
    0.06
    Act Density 0.001%

    No Known Activations