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

    Neuronpedia

    INDEX
    Explanations

    questions and elaborations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    0.57
     each
    0.54
    .
    0.54
     triangular
    0.51
     the
    0.50
    this
    0.49
    fton
    0.49
    ء
    0.48
    kt
    0.47
     every
    0.46
    POSITIVE LOGITS
    特别是
    0.59
     откуда
    0.53
    投資
    0.52
    颖
    0.52
     پس
    0.50
     soprattutto
    0.50
     특히
    0.50
     MAKE
    0.49
    皇家
    0.49
    acelet
    0.48
    Act Density 0.027%

    No Known Activations