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

    Neuronpedia

    INDEX
    Explanations

    pronoun "her" or "she"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aires
    0.52
    erà
    0.46
    роваться
    0.46
     DEL
    0.46
     cargos
    0.45
    yesters
    0.45
     cereals
    0.44
    笏
    0.44
    ಾರ್ಥ
    0.44
    cerer
    0.43
    POSITIVE LOGITS
    5
    0.50
    6
    0.48
    7
    0.47
    9
    0.46
     Squash
    0.45
    亩
    0.44
    Double
    0.43
     Humanitarian
    0.43
    4
    0.43
    0
    0.42
    Act Density 0.041%

    No Known Activations