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

    Neuronpedia

    INDEX
    Explanations

    Fraud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    话
    -0.07
    LoadIdentity
    -0.07
    .lineWidth
    -0.07
    TouchUpInside
    -0.06
    _Style
    -0.06
    近距离
    -0.06
    _GPS
    -0.06
    AccessException
    -0.06
     marché
    -0.06
    _TRACE
    -0.06
    POSITIVE LOGITS
     empowering
    0.08
    icity
    0.07
    京都
    0.07
    雇
    0.07
    .force
    0.07
    .res
    0.07
    โปร
    0.07
     Everton
    0.07
     Pear
    0.07
     Kingdom
    0.07
    Act Density 0.003%

    No Known Activations