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

    Neuronpedia

    INDEX
    Explanations

    questions and apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ual
    -0.07
    lsru
    -0.07
    關�
    -0.07
    ral
    -0.07
    Dst
    -0.07
    zelf
    -0.06
    ˲
    -0.06
     tip
    -0.06
    odate
    -0.06
     del
    -0.06
    POSITIVE LOGITS
    🏛
    0.07
    (Schedulers
    0.07
    .assertNull
    0.07
     poor
    0.07
     Gods
    0.07
    ('''
    0.07
    pressor
    0.07
    爱上
    0.07
     arrogant
    0.07
    公立
    0.07
    Act Density 0.021%

    No Known Activations