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

    Neuronpedia

    INDEX
    Explanations

    scientific methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COMMENT
    -0.07
    icensing
    -0.07
    StandardItem
    -0.07
     股
    -0.07
    rün
    -0.07
     Thanks
    -0.07
    .ensure
    -0.07
    ....↵
    -0.07
     tern
    -0.06
    わけ
    -0.06
    POSITIVE LOGITS
    ¨
    0.06
    ':"
    0.06
     бук
    0.06
    ैस
    0.06
    ANC
    0.06
    ar
    0.06
    madığı
    0.06
    +t
    0.05
    iq
    0.05
    (ag
    0.05
    Act Density 0.038%

    No Known Activations