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

    Neuronpedia

    INDEX
    Explanations

    other with categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TA
    0.71
    時に
    0.62
    ⃝
    0.62
    CE
    0.61
    DA
    0.61
    TLE
    0.60
    BUT
    0.59
     а
    0.59
    TY
    0.58
    Nep
    0.58
    POSITIVE LOGITS
    worldly
    0.74
     altres
    0.63
     mortals
    0.59
     monuments
    0.59
     assorted
    0.57
     aspects
    0.57
    leri
    0.57
     singularities
    0.57
     contenders
    0.56
     collaborations
    0.55
    Act Density 0.023%

    No Known Activations