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

    Neuronpedia

    INDEX
    Explanations

    brainstorming ideas and suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     truly
    0.46
     fluidity
    0.45
     반드시
    0.44
     masterpiece
    0.41
     exquisitely
    0.40
     meticulously
    0.40
    一个是
    0.40
     intimacy
    0.39
     unbedingt
    0.39
    一定要
    0.39
    POSITIVE LOGITS
     brainstorming
    0.69
     ideas
    0.64
     Ideen
    0.64
     brainstorm
    0.64
     suggestions
    0.59
     고민
    0.57
    ideas
    0.57
     questions
    0.55
     टिप्स
    0.55
     Fragen
    0.54
    Act Density 0.036%

    No Known Activations