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

    Neuronpedia

    INDEX
    Explanations

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     İs
    -0.06
    Ap
    -0.06
     XII
    -0.06
     lông
    -0.06
     Reb
    -0.06
    _assignment
    -0.06
    끼
    -0.06
     Contr
    -0.06
     Dew
    -0.06
    ابقه
    -0.06
    POSITIVE LOGITS
     AUDIO
    0.07
     сами
    0.07
    toDate
    0.07
    ball
    0.07
     신
    0.06
    firm
    0.06
    �性
    0.06
     grátis
    0.06
     원
    0.06
    ]+'
    0.06
    Act Density 0.009%

    No Known Activations