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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ụn
    -0.06
    roy
    -0.06
    kup
    -0.06
    ried
    -0.06
    ois
    -0.05
     utterly
    -0.05
     reducer
    -0.05
    рок
    -0.05
     purpos
    -0.05
    ्ड
    -0.05
    POSITIVE LOGITS
     Crimson
    0.08
     YA
    0.07
    识
    0.07
    environments
    0.07
    ])),↵
    0.06
     offsetof
    0.06
     cockpit
    0.06
    (comment
    0.06
    .getResponse
    0.06
    }-{
    0.06
    Act Density 0.008%

    No Known Activations