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

    Neuronpedia

    INDEX
    Explanations

    holographic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.85
    at
    0.81
    도
    0.79
    ar
    0.78
    id
    0.77
    も
    0.75
     hemorrhagic
    0.74
     breadth
    0.73
    و
    0.73
     cardiovascular
    0.73
    POSITIVE LOGITS
     Holog
    1.15
     holog
    1.13
    يها
    1.00
    ↵
    0.95
    ي
    0.89
    ména
    0.87
     ఆదేశ
    0.84
     Мини
    0.84
    stArray
    0.84
     стекла
    0.84
    Act Density 0.004%

    No Known Activations