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

    Neuronpedia

    INDEX
    Explanations

    let followed by action or permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الصحي
    0.92
    로
    0.91
    𝗲
    0.87
    এর
    0.86
     способ
    0.86
     少し
    0.86
     behöver
    0.85
    𝐩
    0.84
     putea
    0.84
    гура
    0.84
    POSITIVE LOGITS
    ting
    1.42
    zte
    1.35
     suffice
    1.31
    izia
    1.28
    know
    1.28
     loose
    1.26
    itia
    1.26
    我知道
    1.26
     theseKeys
    1.23
     slip
    1.21
    Act Density 0.168%

    No Known Activations