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

    Neuronpedia

    INDEX
    Explanations

    Arkansas and Hakone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्ज
    0.42
     Frank
    0.41
     Jay
    0.41
    Frank
    0.36
    柒
    0.36
     κε
    0.36
    argsort
    0.36
    limb
    0.36
     वसूल
    0.36
    槻
    0.36
    POSITIVE LOGITS
     Ou
    0.55
    Ou
    0.51
     OU
    0.46
     ou
    0.45
    OU
    0.44
     garland
    0.41
     Garland
    0.41
     pasting
    0.40
    fou
    0.39
     evapor
    0.38
    Act Density 0.002%

    No Known Activations