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

    Neuronpedia

    INDEX
    Explanations

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    daß
    -0.61
     caviar
    -0.56
     hierogly
    -0.56
     therefore
    -0.56
     ornith
    -0.55
     leprosy
    -0.55
     paddles
    -0.54
     papyrus
    -0.53
     fiddle
    -0.53
     hence
    -0.53
    POSITIVE LOGITS
     The
    0.88
     A
    0.79
     In
    0.79
     We
    0.76
     There
    0.76
     At
    0.75
     For
    0.74
     With
    0.74
     You
    0.73
     As
    0.73
    Act Density 0.107%

    No Known Activations