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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inheritdoc
    -0.08
    >Lorem
    -0.08
    >d
    -0.07
    =d
    -0.07
    ⊿
    -0.07
    �
    -0.07
    Ś
    -0.07
     Dude
    -0.07
    @test
    -0.07
     saddened
    -0.07
    POSITIVE LOGITS
    branch
    0.07
     ls
    0.07
     ()↵
    0.07
     weed
    0.07
    .cn
    0.07
    גישה
    0.07
     hooks
    0.07
    	callback
    0.07
    مش
    0.07
     Вот
    0.07
    Act Density 0.017%

    No Known Activations