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

    Neuronpedia

    INDEX
    Explanations

    social construct of gender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ically
    0.44
     opioids
    0.42
     to
    0.41
     o
    0.41
     electrolytes
    0.40
    offs
    0.40
    bounds
    0.39
    Boston
    0.38
     nucleotides
    0.38
    off
    0.38
    POSITIVE LOGITS
     stessi
    0.56
     இருந்து
    0.48
    เพราะ
    0.46
     mismos
    0.44
     entrambi
    0.44
     самим
    0.44
    getMainUI
    0.44
    /#{
    0.44
     因為
    0.44
     dividido
    0.43
    Act Density 0.001%

    No Known Activations