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

    Neuronpedia

    INDEX
    Explanations

    helpful response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    非常に
    0.61
     انتہائی
    0.48
    superior
    0.46
     매우
    0.46
    effectiveness
    0.45
     indestructible
    0.44
     estremamente
    0.43
     indispensables
    0.43
     extremamente
    0.43
    efficiencies
    0.43
    POSITIVE LOGITS
     fitting
    0.44
    ismic
    0.43
     thoughtful
    0.43
     corresponding
    0.43
     related
    0.42
     reckoned
    0.41
     relevant
    0.41
    相关的
    0.40
     whatever
    0.39
     smart
    0.39
    Act Density 0.012%

    No Known Activations