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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     var
    -0.07
     VAR
    -0.07
     checkboxes
    -0.07
     dat
    -0.06
     travellers
    -0.06
    	case
    -0.06
     covariance
    -0.06
     }).
    -0.06
     guarantees
    -0.06
     guarantee
    -0.06
    POSITIVE LOGITS
    _ASM
    0.07
    ưỡng
    0.07
     Contributor
    0.07
    дяки
    0.06
    ,ep
    0.06
    _episodes
    0.06
    ِن
    0.06
    .twimg
    0.06
     │
    0.06
    USAGE
    0.06
    Act Density 0.044%

    No Known Activations