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

    Neuronpedia

    INDEX
    Explanations

    retrieval and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agę
    0.47
    aggia
    0.45
    avar
    0.41
    说
    0.41
    பி
    0.41
     फ्री
    0.40
    돈
    0.40
    اما
    0.40
    lüsse
    0.39
    胁
    0.39
    POSITIVE LOGITS
     is
    0.46
     inspector
    0.40
     inspectors
    0.39
     seren
    0.39
     introdu
    0.38
     legends
    0.38
     jumping
    0.38
     mother
    0.37
     parents
    0.37
     casc
    0.37
    Act Density 0.000%

    No Known Activations