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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Women
    -0.07
    aintenance
    -0.07
    ivers
    -0.07
     dec
    -0.07
    {text
    -0.06
    549
    -0.06
     MongoDB
    -0.06
    .Children
    -0.06
     Modification
    -0.06
    box
    -0.06
    POSITIVE LOGITS
     ter
    0.07
    орд
    0.06
    gest
    0.06
    @n
    0.06
    nergie
    0.06
     naše
    0.06
     jeune
    0.06
     lle
    0.06
     Gwen
    0.06
     рівня
    0.06
    Act Density 0.003%

    No Known Activations