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

    Neuronpedia

    INDEX
    Explanations

    internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gro
    -0.07
     impartial
    -0.06
    35
    -0.06
    monster
    -0.06
     Dul
    -0.06
     rims
    -0.06
    dda
    -0.06
    zend
    -0.06
    ез
    -0.06
    系統
    -0.06
    POSITIVE LOGITS
     investigates
    0.07
     ''↵
    0.07
     avatar
    0.06
     PAY
    0.06
     역
    0.06
     stationary
    0.06
    .Tensor
    0.06
    ，一
    0.06
    (List
    0.06
    -Origin
    0.06
    Act Density 0.129%

    No Known Activations