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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ۹
    -0.08
     Medina
    -0.06
     gusta
    -0.06
     avere
    -0.06
    �
    -0.06
    jur
    -0.06
    adress
    -0.06
     المنطقة
    -0.06
     remix
    -0.06
    strtotime
    -0.06
    POSITIVE LOGITS
     spicy
    0.07
     justices
    0.06
    .cn
    0.06
     wird
    0.06
     <>
    0.06
     Citation
    0.06
     describe
    0.06
    _encrypt
    0.06
    -windows
    0.06
     axiom
    0.06
    Act Density 0.000%

    No Known Activations