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

    Neuronpedia

    INDEX
    Explanations

    outcome andtips for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮈ
    0.50
    ۸
    0.48
    Би
    0.47
    레
    0.46
    시간
    0.45
    ေ
    0.45
    ర
    0.44
    노
    0.43
    ೌ
    0.43
    타
    0.43
    POSITIVE LOGITS
     заинтере
    0.55
     環境
    0.50
    ระหว่าง
    0.49
     کمپنیوں
    0.47
     بوتل
    0.46
     необхід
    0.46
     العلام
    0.46
     ಪರಿಸ
    0.45
     संपर्क
    0.45
     наві
    0.45
    Act Density 0.000%

    No Known Activations