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

    Neuronpedia

    INDEX
    Explanations

    running software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captain
    -0.07
    _Max
    -0.07
     handleChange
    -0.07
    .dim
    -0.07
     genu
    -0.06
    -max
    -0.06
    errors
    -0.06
     магаз
    -0.06
    prar
    -0.06
    _(
    -0.06
    POSITIVE LOGITS
     casting
    0.06
     somehow
    0.06
    られ
    0.06
     apparent
    0.06
    ↵↵
    0.06
     others
    0.06
     criticizing
    0.06
    .openqa
    0.06
    CCI
    0.06
    سب
    0.06
    Act Density 0.000%

    No Known Activations