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

    Neuronpedia

    INDEX
    Explanations

    confusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	wp
    -0.07
     apo
    -0.07
     соль
    -0.07
     pretext
    -0.07
    .dequeue
    -0.06
     Glasgow
    -0.06
     し
    -0.06
     povin
    -0.06
     workstation
    -0.06
     丶
    -0.06
    POSITIVE LOGITS
    `),↵
    0.07
    erved
    0.07
    resultSet
    0.06
    観
    0.06
    \web
    0.06
    ۳۶
    0.06
    İZ
    0.06
    iếng
    0.06
     rouge
    0.06
     Noise
    0.06
    Act Density 0.005%

    No Known Activations