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

    Neuronpedia

    INDEX
    Explanations

    col

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surrender
    -0.07
     tavern
    -0.07
    `);↵↵
    -0.07
    Invalid
    -0.07
    enefit
    -0.07
     �
    -0.06
     врач
    -0.06
    -con
    -0.06
     sür
    -0.06
     Innovative
    -0.06
    POSITIVE LOGITS
    劁
    0.07
    ㊦
    0.07
     ArgumentException
    0.06
     uintptr
    0.06
     tartış
    0.06
     BEGIN
    0.06
     dee
    0.06
    Ubergraph
    0.06
     iy
    0.06
    骒
    0.06
    Act Density 0.002%

    No Known Activations