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

    Neuronpedia

    INDEX
    Explanations

    calculus applications and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expresiones
    0.43
    េទ
    0.40
     harmed
    0.40
    ithing
    0.39
    levard
    0.39
    गिरी
    0.38
    tim
    0.38
    чня
    0.38
    integrate
    0.38
    visory
    0.37
    POSITIVE LOGITS
     APPLICATIONS
    0.55
     applications
    0.52
    应用的
    0.49
    Applications
    0.48
     Applications
    0.48
     Rates
    0.46
     تطبيقات
    0.45
    applications
    0.44
    业务
    0.44
    應用
    0.43
    Act Density 0.006%

    No Known Activations