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

    Neuronpedia

    INDEX
    Explanations

    humans

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Twilight
    -0.08
     BITS
    -0.07
    CHILD
    -0.07
     breakup
    -0.07
     disobed
    -0.07
     Sahara
    -0.07
     nal
    -0.07
     Mali
    -0.07
     Psychic
    -0.07
     Yak
    -0.07
    POSITIVE LOGITS
    如何
    0.08
    �
    0.07
    另
    0.07
     метро
    0.07
    �
    0.07
     irony
    0.07
    ㄹ
    0.07
    (Room
    0.07
     вывод
    0.07
    ;color
    0.07
    Act Density 0.010%

    No Known Activations