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

    Neuronpedia

    INDEX
    Explanations

    pit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superior
    -0.07
     Fle
    -0.06
    蕉
    -0.06
    .constraint
    -0.06
     mins
    -0.06
    _Run
    -0.06
    oland
    -0.06
    592
    -0.06
     frustrated
    -0.06
     ancestry
    -0.06
    POSITIVE LOGITS
    θλη
    0.07
    hlen
    0.07
    amodel
    0.06
     veri
    0.06
    -code
    0.06
     expressive
    0.06
     exploration
    0.06
     incorporates
    0.06
     swallow
    0.06
    unding
    0.06
    Act Density 0.205%

    No Known Activations