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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Courier
    -0.07
     Boots
    -0.07
    Ev
    -0.07
     Seeds
    -0.07
    able
    -0.07
     Threat
    -0.06
     Congressman
    -0.06
     contradictory
    -0.06
    Attack
    -0.06
     articulate
    -0.06
    POSITIVE LOGITS
     foo
    0.06
    .RowStyle
    0.06
    ))){↵
    0.06
     upt
    0.06
     advertisers
    0.06
     setbacks
    0.06
    特色
    0.06
     displays
    0.06
    ぼ
    0.06
    .setHeader
    0.06
    Act Density 0.081%

    No Known Activations