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

    Neuronpedia

    INDEX
    Explanations

    rotation, constant, new, infection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    klop
    0.50
    znál
    0.49
     alebo
    0.46
     čp
    0.46
    primes
    0.45
    ères
    0.45
    Za
    0.44
    Kaz
    0.44
     रॉ
    0.44
    Kya
    0.44
    POSITIVE LOGITS
     workshop
    0.48
     distilling
    0.47
     distillation
    0.47
     voyage
    0.46
     practical
    0.46
     survival
    0.46
     biomarker
    0.46
     superstructure
    0.45
     deviation
    0.45
     custodian
    0.45
    Act Density 0.005%

    No Known Activations