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

    Neuronpedia

    INDEX
    Explanations

    safety guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *b
    -0.07
    _profit
    -0.07
     minimizing
    -0.06
     Society
    -0.06
     degli
    -0.06
     enfer
    -0.06
    Gar
    -0.06
     du
    -0.06
    togroup
    -0.06
    uling
    -0.06
    POSITIVE LOGITS
     entitlement
    0.06
    -legged
    0.06
    .fasta
    0.06
     одне
    0.06
    :::::
    0.06
    Rotor
    0.06
     trata
    0.06
     �
    0.06
     pět
    0.06
    เมตร
    0.06
    Act Density 0.038%

    No Known Activations