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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     limite
    -0.06
    igung
    -0.06
     descri
    -0.06
    관
    -0.06
     انر
    -0.06
     fastest
    -0.06
     Lebens
    -0.06
    合
    -0.06
    itious
    -0.06
    _every
    -0.06
    POSITIVE LOGITS
     lol
    0.07
    Request
    0.07
    =temp
    0.07
     kin
    0.07
    пол
    0.06
    Michelle
    0.06
    Mahon
    0.06
     kW
    0.06
    池
    0.06
    --------------------------------------------------------------------------↵
    0.06
    Act Density 0.003%

    No Known Activations