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

    Neuronpedia

    INDEX
    Explanations

    sexually suggestive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणि
    0.49
     также
    0.47
     também
    0.46
     hingegen
    0.46
     also
    0.45
     cũng
    0.45
     juga
    0.45
     voilà
    0.45
     asimismo
    0.45
     también
    0.43
    POSITIVE LOGITS
    0.58
    ɪ
    0.49
    Ს
    0.49
    0.46
    ⃣
    0.44
     ं
    0.43
    0.43
             
    0.42
            
    0.42
    rones
    0.42
    Act Density 0.045%

    No Known Activations