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

    Neuronpedia

    INDEX
    Explanations

    exploring, about, implies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Symptoms
    0.45
     Kepala
    0.44
    准备
    0.43
     Horizon
    0.43
     симпто
    0.43
    Symptoms
    0.42
    开始
    0.42
    ເຄ
    0.41
     symptoms
    0.41
    Depuis
    0.41
    POSITIVE LOGITS
     প্রভৃতি
    0.49
     numerosos
    0.47
     PAYMENT
    0.45
    legal
    0.44
     dân
    0.44
    用水
    0.44
     liquidate
    0.43
    various
    0.43
     pavattati
    0.43
     barter
    0.43
    Act Density 0.015%

    No Known Activations