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
    Phrase
    -0.06
     funct
    -0.06
     Piano
    -0.06
     groundbreaking
    -0.06
    //----------------------------------------------------------------
    -0.06
    洲
    -0.06
    cdr
    -0.06
    ît
    -0.05
    byname
    -0.05
    cause
    -0.05
    POSITIVE LOGITS
    มา
    0.07
    Mo
    0.07
     Mo
    0.07
    errar
    0.07
     во
    0.07
    GY
    0.06
     po
    0.06
    <stdio
    0.06
    -menu
    0.06
    (Constants
    0.06
    Act Density 0.067%

    No Known Activations