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

    Neuronpedia

    INDEX
    Explanations

    Java Spring annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UTONIUM
    0.46
     carboxylic
    0.43
     đốt
    0.42
     inlet
    0.41
     escul
    0.40
     islets
    0.40
     orifice
    0.39
     vutta
    0.39
     cadáver
    0.39
     男の子
    0.39
    POSITIVE LOGITS
    class
    0.51
    mood
    0.49
    //
    0.45
    threads
    0.42
    banking
    0.42
    nale
    0.41
    mens
    0.41
    SpringBoot
    0.40
    Mood
    0.39
    Story
    0.39
    Act Density 0.005%

    No Known Activations