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

    Neuronpedia

    INDEX
    Explanations

    feminine pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sedan
    0.41
    𒇽
    0.41
    GREES
    0.40
    િક્
    0.39
     విద్య
    0.38
    ￠
    0.38
    েশ্বর
    0.38
     अवल
    0.37
    ος
    0.37
    revalidator
    0.36
    POSITIVE LOGITS
     she
    0.63
     вона
    0.54
    she
    0.51
    She
    0.49
    她
    0.48
     She
    0.47
     она
    0.45
    uka
    0.43
     她
    0.41
    迢
    0.41
    Act Density 0.000%

    No Known Activations