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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fac
    -0.08
     |
↵
    -0.07
    物理
    -0.07
    commended
    -0.06
    iliate
    -0.06
     makin
    -0.06
    пос
    -0.06
    应当
    -0.06
    VELO
    -0.06
    ectar
    -0.06
    POSITIVE LOGITS
     smr
    0.07
    _OBJECT
    0.06
    .chars
    0.06
     mastered
    0.06
    วย
    0.06
     gathered
    0.06
     erle
    0.06
    _NOW
    0.06
     волос
    0.05
    .assertFalse
    0.05
    Act Density 0.107%

    No Known Activations