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

    Neuronpedia

    INDEX
    Explanations

    plot points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    상의
    -0.08
     Spe
    -0.07
     doucement
    -0.07
    Spe
    -0.07
     internetu
    -0.07
     pione
    -0.07
     Inuit
    -0.07
    Stud
    -0.07
     абсолютно
    -0.07
    uar
    -0.07
    POSITIVE LOGITS
     breakthroughs
    0.10
     crises
    0.09
    高潮
    0.09
     checkpoint
    0.09
    Checkpoint
    0.09
    checkpoint
    0.09
     denying
    0.08
    爆
    0.08
     locator
    0.08
     mid
    0.08
    Act Density 0.013%

    No Known Activations