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

    Neuronpedia

    INDEX
    Explanations

    extraction/isolation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     membres
    -0.08
    EndInit
    -0.07
    �
    -0.07
    --*/↵
    -0.07
     filmmaker
    -0.07
    	ds
    -0.07
    osa
    -0.06
     mixed
    -0.06
    дрес
    -0.06
     Es
    -0.06
    POSITIVE LOGITS
     Remain
    0.07
    jenis
    0.06
    etically
    0.06
    RATE
    0.06
    Amazon
    0.06
    Steel
    0.06
    -make
    0.06
     steel
    0.06
    Turning
    0.06
     machining
    0.06
    Act Density 0.012%

    No Known Activations