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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бо
    -0.07
     Franz
    -0.07
     arson
    -0.07
    μφωνα
    -0.06
     Deutschland
    -0.06
     Dickinson
    -0.06
    叫
    -0.06
     Israeli
    -0.06
     Abe
    -0.06
    ┴
    -0.06
    POSITIVE LOGITS
     hran
    0.07
    -shell
    0.07
    critical
    0.06
    .Utils
    0.06
     (�
    0.06
    _FL
    0.06
     pr
    0.06
    tě
    0.06
    	UFUNCTION
    0.06
     affecting
    0.06
    Act Density 0.005%

    No Known Activations