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

    Neuronpedia

    INDEX
    Explanations

    more than, better than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.52
    ।
    0.41
    ，
    0.39
    ។
    0.37
    ；
    0.36
     ，
    0.35
    '.
    0.35
     এছাড়াও
    0.35
     obwohl
    0.34
    。\
    0.33
    POSITIVE LOGITS
     kuin
    0.53
     than
    0.52
     decât
    0.49
     daripada
    0.41
    than
    0.41
    보다는
    0.40
     preferable
    0.38
     niż
    0.38
     чем
    0.37
     plutôt
    0.36
    Act Density 0.104%

    No Known Activations