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
     reads
    -0.07
     service
    -0.06
     deemed
    -0.06
    .Button
    -0.06
     fronts
    -0.06
     invented
    -0.06
    throws
    -0.06
    Cookie
    -0.06
    }",
    -0.06
     Chinese
    -0.05
    POSITIVE LOGITS
    ulares
    0.07
    trfs
    0.07
    BUTTONDOWN
    0.07
     Switzerland
    0.06
     habil
    0.06
    =localhost
    0.06
    pill
    0.06
     trainable
    0.06
    AUT
    0.06
    _LOADING
    0.06
    Act Density 0.055%

    No Known Activations