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

    Neuronpedia

    INDEX
    Explanations

    women's roles and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    子供
    0.76
     kinderen
    0.75
    ítja
    0.70
    戦略
    0.67
     लेसन
    0.67
     welchen
    0.66
    ကလေး
    0.65
     ölüm
    0.64
    郋
    0.64
    㡴
    0.64
    POSITIVE LOGITS
    CIA
    0.67
     CIA
    0.65
     പി
    0.64
    TY
    0.63
    ply
    0.63
     bypass
    0.63
     relatively
    0.60
    orty
    0.60
    by
    0.59
     PEP
    0.58
    Act Density 0.000%

    No Known Activations