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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curly
    -0.07
     empt
    -0.07
     Certif
    -0.07
     landslide
    -0.06
    elopment
    -0.06
     emo
    -0.06
     leftovers
    -0.06
     pulp
    -0.06
     freezes
    -0.06
    .StylePriority
    -0.06
    POSITIVE LOGITS
    -known
    0.10
     renowned
    0.07
    Regions
    0.06
    _kv
    0.06
    T
    0.06
     국가
    0.06
    وك
    0.06
    _WEEK
    0.06
     allem
    0.06
     Heart
    0.06
    Act Density 0.008%

    No Known Activations