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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    数据
    -0.07
    گه
    -0.07
    _TRAIN
    -0.06
     pillars
    -0.06
    ชม
    -0.06
     Grey
    -0.06
     Κατηγορία
    -0.06
     cultured
    -0.06
    xae
    -0.06
     proclamation
    -0.06
    POSITIVE LOGITS
     equals
    0.07
     incluso
    0.06
    iot
    0.06
    =S
    0.06
    wik
    0.06
    rightarrow
    0.06
    رق
    0.06
    .autoconfigure
    0.06
     into
    0.06
    =\
    0.06
    Act Density 0.012%

    No Known Activations