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

    Neuronpedia

    INDEX
    Explanations

    measure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vidia
    -0.09
    aptops
    -0.09
    抢
    -0.09
     gadgets
    -0.08
     recess
    -0.08
    筋
    -0.08
    ato
    -0.07
     fighting
    -0.07
    悟
    -0.07
    indrome
    -0.07
    POSITIVE LOGITS
     распредел
    0.08
    .Inject
    0.08
     distributions
    0.07
    орт
    0.07
     वितरण
    0.07
     distribution
    0.07
    .inject
    0.07
     DISTR
    0.07
     migr
    0.07
    קה
    0.07
    Act Density 0.003%

    No Known Activations