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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Splash
    -0.07
    ********
    -0.06
     Laf
    -0.06
     Provider
    -0.06
    œ
    -0.06
    ASP
    -0.06
     Kart
    -0.05
     tup
    -0.05
    391
    -0.05
    >).
    -0.05
    POSITIVE LOGITS
    の中
    0.07
    0.07
    _STATIC
    0.07
     Against
    0.07
     بلغ
    0.07
     contribution
    0.06
     /(
    0.06
    (express
    0.06
     torment
    0.06
    �다
    0.06
    Act Density 0.008%

    No Known Activations