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

    Neuronpedia

    INDEX
    Explanations

    boys and men

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Empresa
    0.50
     Forschungs
    0.50
    mselves
    0.50
    as
    0.48
    د
    0.48
    До
    0.48
     Oven
    0.47
     Bypass
    0.47
    ک
    0.47
    MIN
    0.47
    POSITIVE LOGITS
    volent
    0.79
    opausal
    0.68
    👦
    0.63
    volence
    0.60
    atee
    0.58
     férfi
    0.55
     bearded
    0.54
     gentleman
    0.54
     muž
    0.53
    ชาย
    0.53
    Act Density 0.036%

    No Known Activations