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

    Neuronpedia

    INDEX
    Explanations

    moderation/interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ґ
    -0.07
    Preference
    -0.06
     TTL
    -0.06
     ￣
    -0.06
    {(
    -0.06
     zayıf
    -0.06
     Padres
    -0.06
    حة
    -0.06
     αν
    -0.06
     configparser
    -0.06
    POSITIVE LOGITS
     Ethiopia
    0.07
     Sections
    0.07
    ····
    0.07
    /App
    0.07
    κλη
    0.06
     grayscale
    0.06
    CLUDING
    0.06
    tensor
    0.06
     profiling
    0.06
    RCT
    0.06
    Act Density 0.008%

    No Known Activations