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

    Neuronpedia

    INDEX
    Explanations

    Health guidelines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecké
    -0.07
     swallowed
    -0.06
     Phill
    -0.06
     disgust
    -0.06
    (records
    -0.06
    perial
    -0.06
     kø
    -0.06
     ramen
    -0.06
    amble
    -0.06
    exec
    -0.06
    POSITIVE LOGITS
    consulta
    0.07
    }
    0.07
     soundtrack
    0.06
     designate
    0.06
    WITHOUT
    0.06
    ﾟ
    0.06
    tracks
    0.06
    冬
    0.06
     Medium
    0.06
     conditional
    0.06
    Act Density 0.000%

    No Known Activations