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

    Neuronpedia

    INDEX
    Explanations

    workshops and sessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     malaria
    0.34
     Malaria
    0.31
     the
    0.29
     Ou
    0.29
    を使った
    0.29
    ="
    0.29
    م
    0.29
     strategy
    0.29
     NSLog
    0.29
     this
    0.28
    POSITIVE LOGITS
     आयोजित
    0.43
    goers
    0.39
     diadakan
    0.39
    sessions
    0.38
     seminars
    0.38
     sessions
    0.38
     attended
    0.37
    を開催
    0.37
     встречи
    0.36
     অনুষ্ঠিত
    0.35
    Act Density 0.118%

    No Known Activations