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

    Neuronpedia

    INDEX
    Explanations

    controlling the center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     difficulties
    0.44
    ković
    0.43
     potential
    0.43
    kovic
    0.42
     quarterbacks
    0.40
     potentially
    0.40
     facil
    0.40
     danger
    0.39
     erfol
    0.38
     dangers
    0.38
    POSITIVE LOGITS
     memanfaatkan
    0.59
    正しい
    0.56
    利用
    0.55
     aprovechar
    0.53
     utilize
    0.52
     利用
    0.51
     правильно
    0.50
     Utilize
    0.50
     Discipline
    0.50
     aproveitar
    0.49
    Act Density 0.010%

    No Known Activations