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

    Neuronpedia

    INDEX
    Explanations

    he's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eloquence
    1.13
     jūs
    1.08
     prospectus
    1.02
     poils
    1.02
     де
    1.01
     поговорим
    0.99
    ｇ
    0.99
     pergunt
    0.98
    ..........
    0.98
    h
    0.98
    POSITIVE LOGITS
     Même
    1.27
     prévue
    1.16
    가
    1.16
    ॉयड
    1.15
    ताओं
    1.13
    iť
    1.13
    しまった
    1.08
    并将
    1.08
    惯
    1.08
    数字化
    1.07
    Act Density 0.507%

    No Known Activations