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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Suc
    -0.07
     Dr
    -0.06
    	as
    -0.06
     memory
    -0.06
    answer
    -0.06
    _books
    -0.06
    eax
    -0.06
    див
    -0.06
    델
    -0.06
     망
    -0.06
    POSITIVE LOGITS
     abril
    0.06
     temiz
    0.06
     woke
    0.06
    ETA
    0.06
     pošk
    0.06
     testCase
    0.06
    valor
    0.06
    `↵
    0.06
     Anita
    0.05
     {})↵
    0.05
    Act Density 0.003%

    No Known Activations