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

    Neuronpedia

    INDEX
    Explanations

    Nonsense words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     none
    -0.07
     `<
    -0.07
     بط
    -0.07
     consent
    -0.07
    ию
    -0.06
     shutdown
    -0.06
     [:
    -0.06
     Set
    -0.06
    272
    -0.06
     person
    -0.06
    POSITIVE LOGITS
     Ả
    0.07
    jour
    0.07
    buquerque
    0.06
     uděl
    0.06
    _PROPERTIES
    0.06
    ráf
    0.06
    lei
    0.06
    �
    0.06
    .getEnd
    0.06
    fen
    0.06
    Act Density 0.111%

    No Known Activations