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

    Neuronpedia

    INDEX
    Explanations

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samud
    0.66
    Attenuation
    0.60
    ICPSR
    0.57
     cerdo
    0.56
     symplect
    0.55
     échanc
    0.55
    helby
    0.55
    Imidazole
    0.54
     sensi
    0.54
    礻
    0.54
    POSITIVE LOGITS
    ো
    0.75
    н
    0.71
    M
    0.67
    و
    0.67
    D
    0.66
    ন
    0.66
    O
    0.63
    ag
    0.63
    od
    0.61
    the
    0.61
    Act Density 0.000%

    No Known Activations