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

    Neuronpedia

    INDEX
    Explanations

    list of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jr
    1.23
     Revisited
    1.17
    ,
    1.03
     Junior
    0.99
     Hydrochloride
    0.97
    ®,
    0.95
     Esq
    0.90
     célèbre
    0.89
     Airport
    0.88
     Sr
    0.88
    POSITIVE LOGITS
    number
    0.71
    cantidad
    0.70
    linspace
    0.70
    எ
    0.69
    url
    0.67
    other
    0.67
    message
    0.66
    numbers
    0.66
    size
    0.64
    increase
    0.63
    Act Density 0.058%

    No Known Activations