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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cum
    -0.07
     Hilton
    -0.07
    Snow
    -0.07
    Kn
    -0.07
    사이
    -0.07
    .rule
    -0.07
    .refs
    -0.06
    İN
    -0.06
    _Page
    -0.06
     Bew
    -0.06
    POSITIVE LOGITS
    टर
    0.06
     releg
    0.06
     statues
    0.06
    imuth
    0.06
    erged
    0.06
    _AT
    0.06
    ิจารณ
    0.06
     korum
    0.06
     sketch
    0.06
     serene
    0.05
    Act Density 0.007%

    No Known Activations