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

    Neuronpedia

    INDEX
    Explanations

    Le

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rein
    -0.07
     drowned
    -0.06
     rak
    -0.06
     referenced
    -0.06
     gesch
    -0.06
     heraus
    -0.06
     valide
    -0.06
     вып
    -0.05
     společně
    -0.05
     행
    -0.05
    POSITIVE LOGITS
     attaches
    0.07
    -lasting
    0.07
    ohen
    0.06
    banks
    0.06
    ocommerce
    0.06
     girlfriends
    0.06
    ::::::::::::::
    0.06
     reserves
    0.06
    //[
    0.06
    شود
    0.06
    Act Density 0.000%

    No Known Activations