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

    Neuronpedia

    INDEX
    Explanations

    IDs or codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -out
    -0.07
    licit
    -0.07
    �
    -0.07
    شت
    -0.07
    `
↵
    -0.06
     жит
    -0.06
    rá
    -0.06
    eday
    -0.06
    اى
    -0.06
    out
    -0.06
    POSITIVE LOGITS
    )|(
    0.07
     dej
    0.07
     need
    0.07
     cabel
    0.06
    ↵
↵
↵
    0.06
    acje
    0.06
     j
    0.06
     immutable
    0.06
     besoin
    0.06
    ektör
    0.06
    Act Density 0.013%

    No Known Activations