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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circulação
    -0.09
     Bureau
    -0.08
     Yard
    -0.08
     hemorrho
    -0.08
     curtain
    -0.08
     luxurious
    -0.07
     hive
    -0.07
     güzel
    -0.07
     mər
    -0.07
     سخت
    -0.07
    POSITIVE LOGITS
     protagonist
    0.12
     protagonista
    0.12
     ನಾಯಕ
    0.10
     liderazgo
    0.09
     Empower
    0.09
     protagon
    0.09
     heroic
    0.08
     overarching
    0.08
    tagon
    0.08
     aventure
    0.08
    Act Density 0.048%

    No Known Activations