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

    Neuronpedia

    INDEX
    Explanations

    size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Refriger
    -0.07
     cá
    -0.07
    rani
    -0.06
    Có
    -0.06
    ındır
    -0.06
    Directed
    -0.06
    _Widget
    -0.06
     zayıf
    -0.06
    agged
    -0.06
    '].'</
    -0.06
    POSITIVE LOGITS
    (Customer
    0.07
     Vintage
    0.07
    ourke
    0.07
    (sub
    0.07
    _BOUNDS
    0.07
     hockey
    0.07
    standard
    0.07
    UILD
    0.07
    -standard
    0.07
     quiet
    0.07
    Act Density 0.176%

    No Known Activations