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

    Neuronpedia

    INDEX
    Explanations

    automated assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ไฟ
    -0.07
    orrar
    -0.06
     Hal
    -0.06
     ↵        ↵
    -0.06
    ů
    -0.06
    idla
    -0.06
    paque
    -0.06
    ByText
    -0.05
    ernal
    -0.05
    _la
    -0.05
    POSITIVE LOGITS
     Drive
    0.07
     még
    0.06
    -parts
    0.06
     który
    0.06
     instantiation
    0.06
    оці
    0.06
     SEND
    0.06
    “He
    0.06
    niest
    0.06
     :"
    0.06
    Act Density 0.095%

    No Known Activations