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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raiders
    -0.08
    ابع
    -0.07
     운영
    -0.07
    aların
    -0.06
    ΟΔ
    -0.06
    �
    -0.06
    活
    -0.06
    laden
    -0.06
    �
    -0.06
     flux
    -0.06
    POSITIVE LOGITS
     между
    0.06
     Bunny
    0.06
    hcp
    0.06
     fotoğraf
    0.06
     atual
    0.06
     donde
    0.06
     Host
    0.06
     Pale
    0.06
     Public
    0.06
     grâce
    0.06
    Act Density 0.059%

    No Known Activations