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

    Neuronpedia

    INDEX
    Explanations

    Billy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peats
    -0.07
     beg
    -0.07
     cele
    -0.07
     nebezpeč
    -0.07
     mehr
    -0.06
     Charles
    -0.06
    Cómo
    -0.06
     nob
    -0.06
     ссыл
    -0.06
    ў
    -0.06
    POSITIVE LOGITS
     �
    0.07
    etooth
    0.06
    financial
    0.06
     hol
    0.06
    �
    0.06
     argv
    0.06
    alli
    0.06
    _charset
    0.05
    _wf
    0.05
    NotFoundError
    0.05
    Act Density 0.001%

    No Known Activations