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
     Monaco
    -0.07
     Shanghai
    -0.06
     Hector
    -0.06
     debuted
    -0.06
    _des
    -0.06
    _json
    -0.06
     antagon
    -0.06
    Alert
    -0.06
    868
    -0.06
    \"><
    -0.06
    POSITIVE LOGITS
     pornofil
    0.07
    ุณภาพ
    0.07
     scenery
    0.07
     làn
    0.07
     tts
    0.06
     epile
    0.06
    /big
    0.06
     �
    0.06
     發
    0.06
    yon
    0.06
    Act Density 0.037%

    No Known Activations