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

    Neuronpedia

    INDEX
    Explanations

    mucin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    link
    -0.07
     vrou
    -0.07
     於
    -0.06
    Joint
    -0.06
    .da
    -0.06
    Все
    -0.06
    浮
    -0.06
    ча
    -0.06
    ництво
    -0.06
    ман
    -0.06
    POSITIVE LOGITS
     removeFromSuperview
    0.07
    ousands
    0.07
     require
    0.06
    etable
    0.06
    .chars
    0.06
    \Url
    0.06
    .visitMethodInsn
    0.06
    (QStringLiteral
    0.06
     Miche
    0.06
    ');");↵
    0.06
    Act Density 0.008%

    No Known Activations