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

    Neuronpedia

    INDEX
    Explanations

    Your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Justin
    -0.07
    -grand
    -0.06
     grandparents
    -0.06
    apiKey
    -0.06
    unate
    -0.06
    erala
    -0.06
     began
    -0.06
    TERNAL
    -0.06
    Justin
    -0.06
    upd
    -0.06
    POSITIVE LOGITS
    χές
    0.08
    mensaje
    0.07
     органів
    0.07
    ρίς
    0.07
     длин
    0.06
    cence
    0.06
     －
    0.06
     마음
    0.06
    _OM
    0.06
    __(
    0.06
    Act Density 0.021%

    No Known Activations