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

    Neuronpedia

    INDEX
    Explanations

    complications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    жения
    -0.07
     �
    -0.07
    abant
    -0.06
    atab
    -0.06
     snaží
    -0.06
     林
    -0.06
    alen
    -0.06
    _Label
    -0.06
    (sensor
    -0.06
    concat
    -0.06
    POSITIVE LOGITS
    camatan
    0.07
     shit
    0.06
    ."',
    0.06
    .uri
    0.06
    ــ
    0.06
    ?url
    0.06
    international
    0.06
     Afghanistan
    0.06
    cessive
    0.06
    _ca
    0.06
    Act Density 0.008%

    No Known Activations