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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     존
    -0.06
    ÜRK
    -0.06
     represents
    -0.06
    oralType
    -0.06
    .multi
    -0.06
    月
    -0.06
    maf
    -0.06
    άκ
    -0.06
     Meg
    -0.06
    Dani
    -0.05
    POSITIVE LOGITS
     biçim
    0.07
    080
    0.07
    inta
    0.07
    urning
    0.07
    欠
    0.06
     bietet
    0.06
    強
    0.06
     prevented
    0.06
    atomy
    0.06
     ro
    0.06
    Act Density 0.000%

    No Known Activations