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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تی
    -0.07
    NEL
    -0.07
    Fund
    -0.07
    .od
    -0.07
    Tau
    -0.07
    vají
    -0.07
    inals
    -0.07
    lád
    -0.06
    emas
    -0.06
    Filters
    -0.06
    POSITIVE LOGITS
     простран
    0.07
    255
    0.07
     ern
    0.06
    _esc
    0.06
     Ρ
    0.06
     Làm
    0.06
     Adapter
    0.06
     boredom
    0.06
    \OptionsResolver
    0.06
     Nested
    0.06
    Act Density 0.009%

    No Known Activations