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

    Neuronpedia

    INDEX
    Explanations

    baking recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _buf
    -0.08
     provision
    -0.06
    쓰
    -0.06
     museums
    -0.06
     волод
    -0.06
     teamed
    -0.06
     چین
    -0.06
     deline
    -0.06
     escaped
    -0.06
    rientation
    -0.06
    POSITIVE LOGITS
    梯
    0.07
    frag
    0.07
    ｭ
    0.07
     datingsider
    0.06
     мат
    0.06
    .success
    0.06
     /**↵
    0.06
    .rest
    0.06
    _REG
    0.06
     παι
    0.06
    Act Density 0.008%

    No Known Activations