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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    汲
    -0.07
     callable
    -0.07
    আ
    -0.07
    哑
    -0.06
     balk
    -0.06
     сразу
    -0.06
    /print
    -0.06
    .px
    -0.06
     글
    -0.06
    迷惑
    -0.06
    POSITIVE LOGITS
    uish
    0.08
    iere
    0.07
     Duration
    0.07
    .Device
    0.07
    thermal
    0.07
    -admin
    0.07
     Nich
    0.07
    ריש
    0.06
    ellation
    0.06
    erdale
    0.06
    Act Density 0.002%

    No Known Activations