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

    Neuronpedia

    INDEX
    Explanations

    Software fixes/updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cdc
    -0.07
    だ
    -0.07
     temperatura
    -0.07
     cosas
    -0.06
    You
    -0.06
     passwd
    -0.06
    수를
    -0.06
    ides
    -0.06
     You
    -0.06
    ैस
    -0.06
    POSITIVE LOGITS
     Tunis
    0.06
     spurred
    0.06
     Shiite
    0.06
    ALLENG
    0.06
     Trotsky
    0.06
     Toxic
    0.06
    lightly
    0.06
    _geometry
    0.06
    airro
    0.06
    taş
    0.06
    Act Density 0.073%

    No Known Activations