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

    Neuronpedia

    INDEX
    Explanations

    end of for loop condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Len
    0.42
     condition
    0.41
     while
    0.40
    --)
    0.40
     inequalities
    0.39
     clue
    0.38
     inequality
    0.38
     неравен
    0.38
     backwards
    0.38
     <=
    0.37
    POSITIVE LOGITS
    稍
    0.41
    বারেই
    0.41
     Cambrian
    0.41
    ឈ្ម
    0.40
     特に
    0.40
     prefque
    0.40
    Immediately
    0.39
    fileupload
    0.39
    immediately
    0.38
    Li
    0.38
    Act Density 0.002%

    No Known Activations