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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ingerprint
    -0.08
    YPD
    -0.07
    _LA
    -0.07
    ’я
    -0.06
     Hv
    -0.06
    وئ
    -0.06
    液
    -0.06
     Hi
    -0.06
     catering
    -0.06
    incare
    -0.06
    POSITIVE LOGITS
     prostituerade
    0.07
    NotBlank
    0.07
    hole
    0.07
     philosoph
    0.06
    _active
    0.06
     Girl
    0.06
    Bien
    0.06
     Below
    0.06
     DESC
    0.06
     dans
    0.06
    Act Density 0.176%

    No Known Activations