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

    Neuronpedia

    INDEX
    Explanations

    press

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Builders
    -0.06
    riv
    -0.06
     blades
    -0.06
    ズ
    -0.06
     Frozen
    -0.06
     Coc
    -0.06
    _detected
    -0.06
    Runs
    -0.06
    .Nombre
    -0.05
    芯
    -0.05
    POSITIVE LOGITS
    (today
    0.07
     PRESS
    0.07
    κει
    0.07
    -xs
    0.07
    (cancel
    0.06
     Makeup
    0.06
    adores
    0.06
    ЎыџN
    0.06
    ymph
    0.06
     readable
    0.06
    Act Density 0.005%

    No Known Activations