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

    Neuronpedia

    INDEX
    Explanations

    varied contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fac
    -0.07
     emb
    -0.07
     feature
    -0.07
    (ind
    -0.06
     expans
    -0.06
    asa
    -0.06
     aggression
    -0.06
    дан
    -0.06
     तक
    -0.06
    actor
    -0.06
    POSITIVE LOGITS
    ařilo
    0.07
    cházet
    0.07
    ,tp
    0.06
    .visual
    0.06
    postcode
    0.06
    cc
    0.06
     січня
    0.06
    %d
    0.06
     ší
    0.06
     Rusya
    0.06
    Act Density 0.000%

    No Known Activations