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
    elfast
    -0.07
    פנו
    -0.07
    댐
    -0.07
    叶修
    -0.07
    支付
    -0.07
    行程
    -0.07
    fec
    -0.07
    aciente
    -0.07
    FIT
    -0.06
    .cs
    -0.06
    POSITIVE LOGITS
    rones
    0.07
    Projection
    0.07
     Viewer
    0.07
     لأن
    0.07
    𬕂
    0.07
     embedding
    0.07
    _m
    0.07
     burgl
    0.07
    -human
    0.06
    .concatenate
    0.06
    Act Density 0.012%

    No Known Activations