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

    Neuronpedia

    INDEX
    Explanations

    best of list questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    醪
    0.48
     prét
    0.43
     использование
    0.42
     educación
    0.42
    茭
    0.42
    紅茶
    0.42
     О
    0.42
     термо
    0.40
     médicaments
    0.40
    ेशनल
    0.40
    POSITIVE LOGITS
    these
    0.46
    always
    0.44
    diff
    0.41
    retr
    0.41
        
    0.40
     always
    0.40
     this
    0.40
     لهذه
    0.39
         
    0.39
    tra
    0.39
    Act Density 0.007%

    No Known Activations