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

    Neuronpedia

    INDEX
    Explanations

    Contraction "'t"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     were
    -0.06
    Ray
    -0.06
    Mag
    -0.06
    ());↵
    -0.06
    '));↵↵
    -0.06
    Smoke
    -0.06
     criticize
    -0.06
    Mobile
    -0.06
    ()));↵↵
    -0.06
    POSITIVE LOGITS
     سن
    0.08
    آم
    0.08
     Vend
    0.07
     inexperienced
    0.07
     字
    0.07
     PIXI
    0.07
     Habit
    0.07
    днання
    0.07
    จำ
    0.07
    الم
    0.07
    Act Density 0.029%

    No Known Activations