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

    Neuronpedia

    INDEX
    Explanations

    organizational divisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEN
    -0.07
     tur
    -0.06
    fmt
    -0.06
    ados
    -0.06
     scale
    -0.06
    ็บ
    -0.06
    ců
    -0.06
     lime
    -0.06
     Samantha
    -0.06
    UDIO
    -0.06
    POSITIVE LOGITS
    808
    0.06
    821
    0.06
    154
    0.06
    Je
    0.06
    .Popup
    0.06
    าณาจ
    0.06
    _UNS
    0.06
    ща
    0.06
     Helena
    0.06
    lessons
    0.06
    Act Density 0.084%

    No Known Activations