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

    Neuronpedia

    INDEX
    Explanations

    now pause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ants
    0.41
     risk
    0.39
     Dogs
    0.39
     condiment
    0.39
     Helper
    0.38
     attano
    0.37
    できます
    0.37
     Cand
    0.37
     favoriser
    0.37
     placing
    0.36
    POSITIVE LOGITS
    DidChange
    0.44
    ΡΟ
    0.43
     உள்ளிட்ட
    0.42
     मायने
    0.42
    郄
    0.41
    plicht
    0.41
     боли
    0.41
    isempty
    0.40
    वायरमेंट
    0.40
    軺
    0.40
    Act Density 0.001%

    No Known Activations