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

    Neuronpedia

    INDEX
    Explanations

    ere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "Not
    -0.07
     urging
    -0.07
    》的
    -0.06
     novamente
    -0.06
     мг
    -0.06
     suing
    -0.06
     announce
    -0.06
     Allows
    -0.06
     مب
    -0.06
     skew
    -0.06
    POSITIVE LOGITS
    .dirname
    0.10
    ere
    0.10
    eres
    0.10
    _mC
    0.08
    .equalTo
    0.07
    ERE
    0.07
    омер
    0.07
    र
    0.06
     Merry
    0.06
     polov
    0.06
    Act Density 0.002%

    No Known Activations