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

    Neuronpedia

    INDEX
    Explanations

    conviction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lore
    -0.07
     labyrinth
    -0.07
     jelly
    -0.07
     roulette
    -0.07
    416
    -0.06
    ,Y
    -0.06
     Lola
    -0.06
    /interfaces
    -0.06
    해야
    -0.06
     dangers
    -0.06
    POSITIVE LOGITS
     convicted
    0.10
    vt
    0.09
    v
    0.09
     conviction
    0.08
     convictions
    0.08
     convict
    0.08
    伏
    0.07
    Clinical
    0.07
    .iv
    0.07
     erotique
    0.07
    Act Density 0.005%

    No Known Activations