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

    Neuronpedia

    INDEX
    Explanations

    gene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Layout
    -0.07
     Tristan
    -0.07
    <translation
    -0.07
     Socialist
    -0.07
    ROUP
    -0.07
    Chat
    -0.06
     brav
    -0.06
     Roulette
    -0.06
     const
    -0.06
     offsetX
    -0.06
    POSITIVE LOGITS
     genes
    0.11
     gene
    0.11
     Gene
    0.11
    gene
    0.08
     cite
    0.08
     Iranian
    0.07
     ingres
    0.07
     ре
    0.07
    the
    0.07
    ельно
    0.07
    Act Density 0.014%

    No Known Activations