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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Com
    -0.08
     Mother's
    -0.08
     trata
    -0.08
     ABO
    -0.07
     viss
    -0.07
    /a
    -0.07
     Tide
    -0.07
    简称
    -0.07
    .Vertical
    -0.07
    ABB
    -0.07
    POSITIVE LOGITS
     마음
    0.08
     nhớ
    0.08
     minds
    0.08
    doors
    0.08
     hall
    0.08
     nation
    0.07
     Kat
    0.07
    0.07
    ivo
    0.07
     Bewertung
    0.07
    Act Density 0.008%
    No Known Activations