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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     borderline
    -0.07
    /M
    -0.06
     sz
    -0.06
     �
    -0.06
    busters
    -0.06
     NYPD
    -0.06
    asks
    -0.06
     оз
    -0.06
    ΩΝ
    -0.06
    도별
    -0.06
    POSITIVE LOGITS
     Elena
    0.06
     gmail
    0.06
    ाक
    0.06
     cultivate
    0.06
    (txt
    0.06
    /#
    0.06
    _init
    0.06
    OTO
    0.06
     kako
    0.06
     FG
    0.05
    Act Density 0.000%

    No Known Activations