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

    Neuronpedia

    INDEX
    Explanations

    initiator or stabilizer roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Annex
    0.42
    原文
    0.42
    后缀
    0.41
     Versch
    0.40
    法令
    0.40
    мель
    0.40
     Estat
    0.39
     Derived
    0.39
     Trapez
    0.39
     couper
    0.38
    POSITIVE LOGITS
    initro
    0.44
    induction
    0.42
     vegetables
    0.42
    ıyı
    0.41
    ity
    0.40
    kin
    0.39
    nil
    0.38
     induction
    0.38
     종류
    0.38
     song
    0.38
    Act Density 0.001%

    No Known Activations