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

    Neuronpedia

    INDEX
    Explanations

    resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _capture
    -0.07
    ред
    -0.07
     Kunst
    -0.06
    porno
    -0.06
     elim
    -0.06
    _SH
    -0.06
    엄
    -0.06
    	Run
    -0.06
    etur
    -0.06
     attenuation
    -0.06
    POSITIVE LOGITS
     trustworthy
    0.07
    Exact
    0.07
    どこ
    0.07
    "...
    0.07
    "This
    0.06
     newState
    0.06
    Topic
    0.06
    /')
    0.06
     Coch
    0.06
     amazing
    0.06
    Act Density 0.013%

    No Known Activations