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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __*/
    -0.59
    nocześnie
    -0.49
     necesariamente
    -0.47
    BagLayout
    -0.47
     láser
    -0.47
     nevoie
    -0.46
    رر
    -0.46
    ändigt
    -0.46
    不说
    -0.45
     repuesto
    -0.45
    POSITIVE LOGITS
     just
    0.69
     promote
    0.68
     arrive
    0.68
     serve
    0.62
     be
    0.62
     brighten
    0.61
     introduce
    0.61
     respond
    0.61
     resemble
    0.60
     originate
    0.60
    Act Density 0.003%

    No Known Activations