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

    Neuronpedia

    INDEX
    Explanations

    conflict or resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enny
    -0.06
     Negro
    -0.06
    ADF
    -0.06
    া
    -0.06
    uC
    -0.06
     آر
    -0.06
    'int
    -0.06
    ”的
    -0.06
    ımlı
    -0.06
     soğuk
    -0.06
    POSITIVE LOGITS
     ****************************************
    0.07
    semble
    0.07
     speaker
    0.07
     effortlessly
    0.06
     Corrections
    0.06
    ackages
    0.06
    _med
    0.06
    .embedding
    0.06
    ablo
    0.06
    ountains
    0.06
    Act Density 0.055%

    No Known Activations