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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Controls
    -0.07
     disable
    -0.06
    Grid
    -0.06
    Tag
    -0.06
     overlays
    -0.06
     lodge
    -0.06
    /rules
    -0.06
    .Wrap
    -0.06
    -location
    -0.06
    onus
    -0.06
    POSITIVE LOGITS
     عنه
    0.06
    튜
    0.06
     xlink
    0.06
    εύ
    0.06
    िष
    0.06
     krát
    0.06
    Who
    0.06
     �
    0.06
    ्टम
    0.06
     Cabr
    0.06
    Act Density 0.003%

    No Known Activations