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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ust
    -0.06
     argue
    -0.06
     tail
    -0.06
     MP
    -0.06
    你
    -0.06
     fb
    -0.06
     Im
    -0.06
    imin
    -0.06
    -var
    -0.06
    兼
    -0.06
    POSITIVE LOGITS
    家的
    0.07
    ()",
    0.07
    езд
    0.06
     🙂↵↵
    0.06
    winner
    0.06
     onDelete
    0.06
    uilder
    0.06
    .ingredients
    0.06
    -tests
    0.06
    .fetchone
    0.06
    Act Density 0.169%

    No Known Activations