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

    Neuronpedia

    INDEX
    Explanations

    built-in, einsehen, eingängig, Einlage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    notifier
    0.39
     приветствую
    0.37
     علامت
    0.37
     LPTMR
    0.37
     любят
    0.36
     Approximately
    0.36
     удовольствием
    0.36
    KSprite
    0.35
     Exc
    0.35
     کارت
    0.35
    POSITIVE LOGITS
    Institut
    0.44
     Commentary
    0.42
                
    0.41
    allaitement
    0.40
     opinião
    0.40
    ss
    0.39
     bruises
    0.39
     bruising
    0.39
    Opinion
    0.39
               
    0.37
    Act Density 0.001%

    No Known Activations