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

    Neuronpedia

    INDEX
    Explanations

    bridges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弾
    -0.06
    794
    -0.06
    793
    -0.06
    ジ
    -0.06
    (split
    -0.06
     recycle
    -0.06
     scheduling
    -0.06
    ighting
    -0.06
     bỏ
    -0.06
     loosen
    -0.06
    POSITIVE LOGITS
     ejaculation
    0.07
    ây
    0.06
     있음
    0.06
    ्रश
    0.06
    $num
    0.06
    -war
    0.06
     taxable
    0.06
    Uses
    0.06
    atar
    0.06
    gın
    0.06
    Act Density 0.024%

    No Known Activations