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

    Neuronpedia

    INDEX
    Explanations

    cut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     handguns
    -0.07
    에
    -0.07
     yorum
    -0.06
     پول
    -0.06
    nThe
    -0.06
    configured
    -0.06
    _SB
    -0.06
    اسه
    -0.06
    시에
    -0.06
    english
    -0.06
    POSITIVE LOGITS
     ugl
    0.08
     logos
    0.08
     tonic
    0.06
    -bar
    0.06
     usuarios
    0.06
    [word
    0.06
    !).
    0.06
     barber
    0.06
     Gover
    0.06
     Riding
    0.06
    Act Density 0.005%

    No Known Activations