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

    Neuronpedia

    INDEX
    Explanations

    WORD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hôn
    -0.08
     tung
    -0.07
    .cx
    -0.07
    Ltd
    -0.07
    ondheim
    -0.07
    -stream
    -0.07
    傳統
    -0.07
     tienes
    -0.06
    報導
    -0.06
     Resource
    -0.06
    POSITIVE LOGITS
    ㏂
    0.07
     bulbs
    0.07
    aphrag
    0.07
    Stopping
    0.07
     pylab
    0.07
    •↵↵
    0.06
    =>$
    0.06
    ㉮
    0.06
    accur
    0.06
    asper
    0.06
    Act Density 0.001%

    No Known Activations