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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -sec
    -0.09
    835
    -0.08
    Secure
    -0.08
     (?)
    -0.08
     тщательно
    -0.08
     تعالی
    -0.08
    вей
    -0.07
     testified
    -0.07
    ELY
    -0.07
    打造
    -0.07
    POSITIVE LOGITS
     terlalu
    0.09
     invál
    0.09
     слишком
    0.09
     unsupported
    0.08
     invalid
    0.08
     너무
    0.08
     yeter
    0.08
     foreseeable
    0.08
     إد
    0.08
    _invalid
    0.08
    Act Density 0.016%

    No Known Activations