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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Preview
    -0.07
    Pattern
    -0.07
     Interview
    -0.06
    _PROJECT
    -0.06
    ्ञ
    -0.06
    episode
    -0.06
     Powell
    -0.06
    .Pattern
    -0.06
     McConnell
    -0.06
     Samantha
    -0.06
    POSITIVE LOGITS
    addPreferredGap
    0.06
    。」↵↵
    0.06
    Taking
    0.06
    .abstract
    0.06
    ціональ
    0.06
     �
    0.06
    formik
    0.06
     الوطني
    0.06
    _does
    0.06
     vậy
    0.06
    Act Density 0.008%

    No Known Activations