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

    Neuronpedia

    INDEX
    Explanations

    nice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Loads
    -0.07
    CAL
    -0.07
    -------------
    -0.06
     سنة
    -0.06
    _PD
    -0.06
    Federal
    -0.06
     Ezek
    -0.06
    No
    -0.06
    138
    -0.06
    niest
    -0.06
    POSITIVE LOGITS
     nicely
    0.09
     син
    0.07
     Зд
    0.07
     dash
    0.06
    (Response
    0.06
     mük
    0.06
     Zimmer
    0.06
    _REV
    0.06
     folding
    0.06
     Syn
    0.06
    Act Density 0.020%

    No Known Activations