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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yses
    -0.07
     victory
    -0.07
    ,str
    -0.07
    appers
    -0.07
    ائل
    -0.07
    	i
    -0.07
     enc
    -0.07
    オ
    -0.06
    威
    -0.06
    ellers
    -0.06
    POSITIVE LOGITS
     keer
    0.07
    现代
    0.07
    ToPoint
    0.06
     Loan
    0.06
    Lt
    0.06
     interesse
    0.06
    .recipe
    0.06
    ？”↵↵
    0.06
     Tmin
    0.06
     ");
↵
    0.06
    Act Density 0.025%

    No Known Activations