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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ={({
    -0.07
    .Buffer
    -0.07
     전체
    -0.06
     converge
    -0.06
    handleChange
    -0.06
    рей
    -0.06
     expansions
    -0.06
    startDate
    -0.06
    -0.06
    .jetbrains
    -0.06
    POSITIVE LOGITS
     mozilla
    0.08
     Mines
    0.07
    cuador
    0.07
     FileInputStream
    0.07
     cigar
    0.06
    
    0.06
     girlfriends
    0.06
     '|'
    0.06
    Neal
    0.06
     WT
    0.06
    Act Density 0.000%

    No Known Activations