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

    Neuronpedia

    INDEX
    Explanations

    melanin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uran
    -0.07
    .make
    -0.07
     Iraq
    -0.07
    uces
    -0.07
    彩
    -0.06
    'I
    -0.06
    _Object
    -0.06
    ducted
    -0.06
    /internal
    -0.06
    cludes
    -0.06
    POSITIVE LOGITS
    حض
    0.07
    Increases
    0.07
     chilling
    0.07
    AY
    0.07
    bay
    0.07
    营业额
    0.07
     explains
    0.06
     Lamb
    0.06
     doping
    0.06
    -appointed
    0.06
    Act Density 0.008%

    No Known Activations