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

    Neuronpedia

    INDEX
    Explanations

    punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مس
    0.49
    兼用
    0.44
    водство
    0.44
    幅
    0.43
    います
    0.42
    ()")
    0.40
     اخر
    0.40
    уре
    0.40
    வும்
    0.39
    Formatting
    0.39
    POSITIVE LOGITS
     endors
    0.51
     MNC
    0.49
     aphids
    0.49
    ANG
    0.48
     seçim
    0.47
     appreciates
    0.47
     OPEC
    0.46
     amuse
    0.45
     NSE
    0.45
     উপভোগ
    0.45
    Act Density 0.044%

    No Known Activations