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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wary
    -0.06
     gratuiti
    -0.06
     predictable
    -0.06
     Sob
    -0.06
     piel
    -0.06
    lient
    -0.06
     Worst
    -0.06
     dakika
    -0.06
    Qed
    -0.06
     boz
    -0.05
    POSITIVE LOGITS
    alcon
    0.07
     başlam
    0.07
    pm
    0.07
    _pd
    0.07
     competitors
    0.07
     vested
    0.07
     adulthood
    0.07
     lớ
    0.06
    ano
    0.06
    친
    0.06
    Act Density 0.000%

    No Known Activations