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

    Neuronpedia

    INDEX
    Explanations

    true values and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    0.61
    。
    0.59
    </
    0.57
    ↵↵
    0.57
    0.55
    *
    0.52
    ></
    0.47
    EL
    0.46
    ิ
    0.46
    **
    0.45
    POSITIVE LOGITS
     thermocou
    0.52
     तारों
    0.50
     संके
    0.49
     ribosomes
    0.49
     antigens
    0.48
     incess
    0.48
     glycoproteins
    0.48
     преимуще
    0.48
     लाइट्स
    0.48
    𒇉
    0.48
    Act Density 0.001%

    No Known Activations