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

    Neuronpedia

    INDEX
    Explanations

    Warning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    seconds
    -0.07
    .Side
    -0.07
     GER
    -0.06
     Ghost
    -0.06
    _backend
    -0.06
    _xlabel
    -0.06
    .MEDIA
    -0.06
    advertisement
    -0.06
    ayed
    -0.06
     Profile
    -0.06
    POSITIVE LOGITS
     Uz
    0.08
     압
    0.07
    punk
    0.07
    velle
    0.07
    Luc
    0.07
    \controllers
    0.07
    gal
    0.06
     Unsure
    0.06
     simplicity
    0.06
    �
    0.06
    Act Density 0.006%

    No Known Activations