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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    idders
    -0.06
    ﾏ
    -0.06
    είο
    -0.06
     джер
    -0.06
     Manson
    -0.06
     kommer
    -0.06
    cies
    -0.06
    ampire
    -0.06
     expressly
    -0.06
    خب
    -0.05
    POSITIVE LOGITS
     vict
    0.07
    .last
    0.07
     involuntary
    0.07
    =new
    0.07
    .assign
    0.07
    (interface
    0.07
    (matrix
    0.07
     employees
    0.07
    يان
    0.06
    Int
    0.06
    Act Density 0.021%

    No Known Activations