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

    Neuronpedia

    INDEX
    Explanations

    important note for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আশংকা
    0.46
     невозможно
    0.46
    指导
    0.46
     குறிப்பாக
    0.45
    闾
    0.45
    系统
    0.44
    萆
    0.43
    总是
    0.42
    ාවිත
    0.42
     তরঙ্গ
    0.42
    POSITIVE LOGITS
    for
    0.40
     dramas
    0.39
    ’
    0.39
    inue
    0.38
    inin
    0.36
    וד
    0.36
     ra
    0.36
    νοι
    0.35
    iva
    0.35
    dua
    0.35
    Act Density 0.000%

    No Known Activations