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

    Neuronpedia

    INDEX
    Explanations

    URLs and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зяй
    -0.81
     зависит
    -0.78
    を果た
    -0.76
    From
    -0.75
    edipus
    -0.75
    είς
    -0.75
    With
    -0.74
     lontano
    -0.72
    來源
    -0.71
    Τα
    -0.71
    POSITIVE LOGITS
     this
    1.08
    tobe
    0.93
     aspetti
    0.90
    veri
    0.87
    ivity
    0.86
    ildo
    0.85
     &'
    0.85
    InMillis
    0.84
    masters
    0.84
    maic
    0.82
    Act Density 0.001%

    No Known Activations