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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sud
    -0.07
    bc
    -0.06
     Comput
    -0.06
    Presence
    -0.06
    tower
    -0.06
    ंजन
    -0.06
     suburbs
    -0.06
     narc
    -0.06
     Smoking
    -0.06
    unpack
    -0.06
    POSITIVE LOGITS
    /password
    0.07
     danych
    0.06
     prayers
    0.06
     fr
    0.06
    	es
    0.06
     bằng
    0.06
    HONE
    0.06
     Started
    0.06
     unrecognized
    0.06
     happiest
    0.06
    Act Density 0.000%

    No Known Activations