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

    Neuronpedia

    INDEX
    Explanations

    sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     significa
    -0.07
     beaches
    -0.07
    relationships
    -0.07
    ($('.
    -0.06
     Levine
    -0.06
    pliers
    -0.06
    ünüz
    -0.06
     foregoing
    -0.06
    Autom
    -0.06
    sanız
    -0.06
    POSITIVE LOGITS
     etkili
    0.07
     Dairy
    0.06
     Morr
    0.06
    ateg
    0.06
     strt
    0.06
     piece
    0.06
    .hit
    0.06
    .mime
    0.06
     JSONObject
    0.06
    .not
    0.06
    Act Density 0.070%

    No Known Activations