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

    Neuronpedia

    INDEX
    Explanations

    signs and indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     పాల్గొ
    0.80
     பங்கே
    0.74
    opoulos
    0.74
    期間
    0.70
     প্রয়োজন
    0.69
     చేసుకు
    0.68
     ضمن
    0.68
     অংশগ্রহণ
    0.68
    涉及
    0.68
    Compose
    0.67
    POSITIVE LOGITS
     clues
    2.77
     indicators
    2.48
     signs
    2.45
     clue
    2.32
     cues
    2.28
     indicator
    2.24
     Signs
    2.23
    Signs
    2.19
     Indicators
    2.18
    indicators
    2.10
    Act Density 0.540%

    No Known Activations