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

    Neuronpedia

    INDEX
    Explanations

    attributes/measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    monds
    -0.07
    Vers
    -0.07
     hugged
    -0.06
    thur
    -0.06
    �
    -0.06
     ['-
    -0.06
     kẻ
    -0.06
    ortal
    -0.06
     Sanctuary
    -0.06
    addAction
    -0.06
    POSITIVE LOGITS
    .enter
    0.07
    _ADD
    0.07
    λης
    0.07
     الأولى
    0.06
     celebrated
    0.06
     anomalies
    0.06
     в
    0.06
    LAN
    0.06
     guardar
    0.06
     wonderful
    0.06
    Act Density 0.079%

    No Known Activations