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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stration
    -0.07
    匿
    -0.07
    扉
    -0.07
     swapped
    -0.07
    ريب
    -0.06
    聆
    -0.06
    enaire
    -0.06
    ASE
    -0.06
    請您提供
    -0.06
    fällig
    -0.06
    POSITIVE LOGITS
     Crescent
    0.07
    Christmas
    0.07
    getPath
    0.07
     laugh
    0.07
    >T
    0.07
    Oct
    0.06
    文化的
    0.06
    _picture
    0.06
     kne
    0.06
     кров
    0.06
    Act Density 0.012%

    No Known Activations