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

    Neuronpedia

    INDEX
    Explanations

    bright, shining, compelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jata
    0.47
    ploidy
    0.46
    aba
    0.46
    bea
    0.46
    褒
    0.44
    arya
    0.44
    alty
    0.43
    atan
    0.43
    akos
    0.43
    ase
    0.42
    POSITIVE LOGITS
    רא
    0.54
    వ
    0.49
    ಿಕ
    0.48
    лейбол
    0.47
    י
    0.47
    ฑ
    0.47
    ות
    0.47
    细菌
    0.46
    сло
    0.46
    రించ
    0.46
    Act Density 0.002%

    No Known Activations