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

    Neuronpedia

    INDEX
    Explanations

    Difficulties/emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーテ
    -0.08
    査
    -0.07
     very
    -0.06
     fiscal
    -0.06
    νομα
    -0.06
    _swap
    -0.06
    _confirm
    -0.06
     commercial
    -0.06
    -issue
    -0.06
     NOT
    -0.06
    POSITIVE LOGITS
    ……。
    0.07
    ="<<
    0.06
     "!
    0.06
     aşağıdaki
    0.06
    |[
    0.06
    จากการ
    0.06
     lief
    0.06
    *>*
    0.06
    ':"
    0.06
     nước
    0.06
    Act Density 0.098%

    No Known Activations