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

    Neuronpedia

    INDEX
    Explanations

    declarations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cody
    -0.07
     velocities
    -0.06
     innovation
    -0.06
     نظ
    -0.06
     Install
    -0.06
    burn
    -0.06
     Data
    -0.06
    \Base
    -0.06
    Feel
    -0.06
    Think
    -0.06
    POSITIVE LOGITS
     움
    0.06
    eventType
    0.06
    idable
    0.06
    ToLower
    0.06
    KNOWN
    0.06
     advant
    0.06
    ví
    0.06
    ulle
    0.06
     Unicorn
    0.06
    pageNum
    0.06
    Act Density 0.143%

    No Known Activations