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

    Neuronpedia

    INDEX
    Explanations

    data and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afterPath
    0.44
     >
    0.42
    AL
    0.40
     e
    0.40
     converg
    0.40
     Ernesto
    0.40
    at
    0.40
     tern
    0.39
     LPA
    0.39
     mex
    0.39
    POSITIVE LOGITS
    रहे
    0.46
    ക്കള്‍
    0.44
    خدام
    0.43
    WHEN
    0.43
    वाट
    0.41
    隂
    0.41
     పోలీ
    0.40
     तपाईं
    0.40
    ക്കളുടെ
    0.40
    ᱦ
    0.40
    Act Density 0.002%

    No Known Activations