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

    Neuronpedia

    INDEX
    Explanations

    eidetic memory, freedom, business models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نف
    0.48
    sequently
    0.39
    ின்றனர்
    0.39
     Rats
    0.39
    mamm
    0.39
    કોટ
    0.38
    )_
    0.38
    يميديا
    0.38
     Mamm
    0.37
    lessly
    0.37
    POSITIVE LOGITS
     squ
    0.46
    Sec
    0.44
     sec
    0.44
     제곱
    0.44
     Squ
    0.44
     Sec
    0.43
    squ
    0.42
    Squ
    0.39
    obo
    0.38
    arrer
    0.38
    Act Density 0.001%

    No Known Activations