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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ારે
    0.50
    Bali
    0.45
    Lago
    0.44
    нали
    0.43
    علام
    0.42
    ங்க
    0.42
    ло
    0.41
    Semaphore
    0.41
    वंत
    0.40
     শতাব্দ
    0.40
    POSITIVE LOGITS
    situ
    0.56
    in
    0.52
     như
    0.50
     nagu
    0.49
    yor
    0.48
     resid
    0.47
     domain
    0.47
     फु
    0.47
     previos
    0.47
    en
    0.46
    Act Density 0.005%

    No Known Activations