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

    Neuronpedia

    INDEX
    Explanations

    Software licensing text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .spacing
    -0.07
    感动
    -0.07
    荪
    -0.07
     month
    -0.07
    🎣
    -0.07
     חג
    -0.07
    .XtraLayout
    -0.07
     domingo
    -0.07
    了起来
    -0.07
     subscribing
    -0.07
    POSITIVE LOGITS
     Impro
    0.07
     Tro
    0.07
     synthetic
    0.07
    Marshal
    0.06
    .multi
    0.06
     V
    0.06
     proxy
    0.06
     denial
    0.06
    ẓ
    0.06
     refusal
    0.06
    Act Density 0.000%

    No Known Activations