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

    Neuronpedia

    INDEX
    Explanations

    Let followed by a symbol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    となる
    0.44
     bells
    0.44
     they
    0.43
     doesn
    0.43
    σμ
    0.42
    ands
    0.42
    ↵
    0.41
    bells
    0.41
     whether
    0.41
     while
    0.41
    POSITIVE LOGITS
    यॉर्क
    0.45
     была
    0.45
    ValidationError
    0.43
    लोर
    0.42
    क्रमण
    0.39
     كانت
    0.39
     அவள்
    0.39
     ఫి
    0.38
    الان
    0.38
    ୫
    0.38
    Act Density 0.006%

    No Known Activations