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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pools
    -0.08
    “(
    -0.07
    ouden
    -0.07
    プ
    -0.07
    gulp
    -0.07
     Bulls
    -0.07
    Hur
    -0.07
     his
    -0.07
    Outside
    -0.06
    nEnter
    -0.06
    POSITIVE LOGITS
     mieszkań
    0.07
    orias
    0.07
     Additional
    0.06
    Adapter
    0.06
    ۓ
    0.06
    ☲
    0.06
    LineStyle
    0.06
    ísticas
    0.06
    毛泽
    0.06
    _icall
    0.06
    Act Density 0.000%

    No Known Activations