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

    Neuronpedia

    INDEX
    Explanations

    recipe yields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COLLECTION
    0.43
     சிற்ப
    0.40
    '$\
    0.40
    控件
    0.38
    djangoproject
    0.38
     Morley
    0.38
     ভারতীয়
    0.37
    INTERVAL
    0.37
     رج
    0.36
    ']+
    0.36
    POSITIVE LOGITS
     outcome
    0.39
     cond
    0.36
     ispit
    0.35
     consolidate
    0.35
     ll
    0.34
     bush
    0.34
     realistic
    0.34
    ZD
    0.33
     salvage
    0.33
    outcome
    0.32
    Act Density 0.004%

    No Known Activations