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

    Neuronpedia

    INDEX
    Explanations

    dedication and commitment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ใน
    -0.08
     seeds
    -0.08
    领土
    -0.07
     wichtig
    -0.06
     koń
    -0.06
    cfg
    -0.06
    しましょう
    -0.06
    jur
    -0.06
    本
    -0.06
    るので
    -0.06
    POSITIVE LOGITS
    _escape
    0.08
    :first
    0.08
    𝙪
    0.07
     Pe
    0.07
    fff
    0.07
     AFC
    0.07
     [[]
    0.07
     Fiscal
    0.07
     upward
    0.07
    city
    0.06
    Act Density 0.093%

    No Known Activations