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

    Neuronpedia

    INDEX
    Explanations

    burnt food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.65
    л
    0.65
     s
    0.59
    </td>
    0.57
    i
    0.56
     OPEN
    0.54
    T
    0.54
                    
    0.53
    M
    0.53
    ک
    0.52
    POSITIVE LOGITS
    riteria
    0.53
    വൃത്തി
    0.53
    arabangsa
    0.50
    诰
    0.50
    ២
    0.49
    valu
    0.49
    assen
    0.48
    机的
    0.48
    趼
    0.48
    lebn
    0.48
    Act Density 0.001%

    No Known Activations