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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьте
    0.47
     акча
    0.46
     الأساس
    0.46
    время
    0.44
     shockingly
    0.43
     vó
    0.43
    ders
    0.42
     invade
    0.42
     नकार
    0.42
     time
    0.42
    POSITIVE LOGITS
    Material
    0.45
     Pills
    0.43
    दिष्ट
    0.43
    MATERIAL
    0.43
    )，
    0.43
    酵
    0.41
     lineWidth
    0.41
    适用于
    0.40
     σαν
    0.40
    脂肪
    0.39
    Act Density 0.000%

    No Known Activations