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

    Neuronpedia

    INDEX
    Explanations

    machine intelligence/awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Porno
    -0.08
    щих
    -0.08
     Lighting
    -0.07
     diesem
    -0.06
     Там
    -0.06
     epilepsy
    -0.06
     fractions
    -0.06
    대의
    -0.06
    十六
    -0.06
    rolled
    -0.06
    POSITIVE LOGITS
     selfie
    0.07
    徐
    0.06
     toplum
    0.06
     steals
    0.06
     ")↵
    0.06
    Apparently
    0.06
    _FOLLOW
    0.06
    getApplication
    0.06
     probs
    0.06
    ror
    0.06
    Act Density 0.076%

    No Known Activations