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

    Neuronpedia

    INDEX
    Explanations

    academic and professional credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    button
    0.40
    轲
    0.40
    ===
    0.40
    ==="
    0.39
    backends
    0.38
    。。。。
    0.38
    ...."
    0.38
    popularity
    0.38
    ！！！！
    0.37
    😗
    0.37
    POSITIVE LOGITS
     PhD
    0.51
     är
    0.48
    PhD
    0.46
    ®,
    0.44
     Esq
    0.44
     MSc
    0.44
    ,
    0.43
    ED
    0.43
     horas
    0.42
     Certified
    0.42
    Act Density 0.004%

    No Known Activations