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

    Neuronpedia

    INDEX
    Explanations

    character encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سو
    -0.06
     цим
    -0.06
    Cou
    -0.06
    CTS
    -0.06
    Sy
    -0.06
    G
    -0.06
     ensued
    -0.06
     заліз
    -0.06
     доме
    -0.06
    妇
    -0.06
    POSITIVE LOGITS
     Δ
    0.07
    )||
    0.07
     Pedro
    0.06
     Location
    0.06
    (Session
    0.06
     stringBy
    0.06
     smash
    0.06
     Filter
    0.06
    (iter
    0.06
    (cluster
    0.06
    Act Density 0.079%

    No Known Activations