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

    Neuronpedia

    INDEX
    Explanations

    inconsistent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     export
    -0.09
    Export
    -0.08
    Vue
    -0.08
     beteg
    -0.07
     tou
    -0.07
     zim
    -0.07
    �
    -0.07
    Intl
    -0.07
    export
    -0.07
     зим
    -0.07
    POSITIVE LOGITS
     impossible
    0.11
     incompatible
    0.11
     impossível
    0.10
     onmogelijk
    0.10
    Impossible
    0.10
     невозможно
    0.10
     unrealistic
    0.10
     conflicting
    0.10
     Impossible
    0.10
     incompat
    0.10
    Act Density 0.035%

    No Known Activations