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

    Neuronpedia

    INDEX
    Explanations

    questions and conversation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VP
    -0.07
     Henry
    -0.06
     Ruth
    -0.06
     Petty
    -0.06
    158
    -0.06
    adan
    -0.06
    _route
    -0.06
     σχέ
    -0.06
     lup
    -0.06
    806
    -0.06
    POSITIVE LOGITS
     đột
    0.06
     хотел
    0.06
    .terminate
    0.06
    -items
    0.06
    ="">
    0.06
    ubern
    0.06
    :::::::::::::
    0.06
    ениями
    0.06
    .sh
    0.06
    《
    0.06
    Act Density 0.069%

    No Known Activations