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

    Neuronpedia

    INDEX
    Explanations

    female family members

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -funded
    -0.08
     toxicity
    -0.08
    ред
    -0.08
     malicious
    -0.08
    Chains
    -0.08
    601
    -0.08
    Targets
    -0.07
     atrib
    -0.07
     reseller
    -0.07
    gha
    -0.07
    POSITIVE LOGITS
     duties
    0.09
     Duties
    0.09
     lindas
    0.08
     bác
    0.08
    になる
    0.08
     sperm
    0.08
     beautiful
    0.07
     ചടങ്ങ
    0.07
     beautifully
    0.07
    咪
    0.07
    Act Density 0.013%

    No Known Activations