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
     Investor
    -0.07
    .same
    -0.06
    тя
    -0.06
    xes
    -0.06
    .’”↵↵
    -0.06
     Punch
    -0.06
    .');↵↵
    -0.06
    Republican
    -0.05
    AppState
    -0.05
    POCH
    -0.05
    POSITIVE LOGITS
    brig
    0.07
    =null
    0.07
    _BAD
    0.07
    hydro
    0.07
    呈
    0.07
     Diploma
    0.07
    _PROD
    0.06
    hape
    0.06
    िष
    0.06
    งแต
    0.06
    Act Density 0.189%

    No Known Activations