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
    販売
    -0.06
     dedicated
    -0.06
     War
    -0.06
     lấy
    -0.06
     war
    -0.06
     engineered
    -0.06
     listening
    -0.06
    択
    -0.06
     mingle
    -0.06
     disco
    -0.06
    POSITIVE LOGITS
     extortion
    0.07
    Series
    0.07
    �
    0.07
    $res
    0.07
    !!!!!!!!
    0.07
     centroid
    0.07
     useForm
    0.06
    consider
    0.06
    Mari
    0.06
    size
    0.06
    Act Density 0.056%

    No Known Activations