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

    Neuronpedia

    INDEX
    Explanations

    say "before"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сих
    -0.08
    әге
    -0.07
    าที
    -0.07
     zover
    -0.07
     inmiddels
    -0.07
     tweede
    -0.07
     latter
    -0.07
    itize
    -0.07
     گئی
    -0.06
    агыл
    -0.06
    POSITIVE LOGITS
     before
    0.80
    before
    0.73
     sebelum
    0.71
    Before
    0.71
     Before
    0.70
     antes
    0.70
    _before
    0.69
     abans
    0.66
    	before
    0.65
     voordat
    0.64
    Act Density 1.092%

    No Known Activations