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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _math
    -0.07
     आश
    -0.06
     Advoc
    -0.06
     الكه
    -0.06
     cif
    -0.06
     Confeder
    -0.06
    ometown
    -0.06
     هل
    -0.06
    طف
    -0.06
    n
    -0.06
    POSITIVE LOGITS
    _BOUNDS
    0.07
     deserialize
    0.06
    !)
    0.06
    ulos
    0.06
     граду
    0.06
    Except
    0.06
    ialized
    0.06
     gate
    0.06
     berg
    0.06
    resents
    0.06
    Act Density 0.007%

    No Known Activations