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
     podrás
    -0.08
    reden
    -0.08
    sprintf
    -0.07
     болып
    -0.07
     Zuf
    -0.07
     gesetzt
    -0.07
     proudly
    -0.07
    -0.07
    性交
    -0.07
    -0.07
    POSITIVE LOGITS
     NG
    0.08
     None
    0.08
     NT
    0.07
     perspectives
    0.07
     nasa
    0.07
    851
    0.07
    NG
    0.07
    XXX
    0.07
    879
    0.07
     movements
    0.07
    Act Density 0.037%
    No Known Activations