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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     теперь
    -0.08
     disponível
    -0.07
     hope
    -0.07
     diverses
    -0.07
    liness
    -0.07
     contém
    -0.07
     vielfält
    -0.07
    dea
    -0.07
     available
    -0.07
    ástico
    -0.07
    POSITIVE LOGITS
     midst
    0.10
     संक्रमण
    0.09
    Transition
    0.09
    _SB
    0.08
     διάρκεια
    0.08
    ುತ್ತಿದ್ದ
    0.08
    _transition
    0.08
     Transition
    0.08
    _TRANS
    0.08
     진행
    0.08
    Act Density 0.033%

    No Known Activations