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

    Neuronpedia

    INDEX
    Explanations

    Gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prs
    -0.06
     Secrets
    -0.06
    press
    -0.06
     आदम
    -0.06
    ρο
    -0.06
     ifad
    -0.06
     luder
    -0.06
     Wig
    -0.06
     irre
    -0.06
     devout
    -0.06
    POSITIVE LOGITS
    listener
    0.07
    indice
    0.06
    Documentation
    0.06
    ίνεται
    0.06
    /results
    0.06
     regardless
    0.06
     Indicator
    0.06
     guide
    0.06
    STEM
    0.06
    zí
    0.06
    Act Density 0.004%

    No Known Activations