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

    Neuronpedia

    INDEX
    Explanations

    specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কানিক্যাল
    0.39
     })(
    0.37
     ओलंप
    0.36
     voie
    0.36
    节点的
    0.35
     Examin
    0.35
     धमकी
    0.35
     '\\
    0.35
     বটে
    0.35
     कंस
    0.34
    POSITIVE LOGITS
    jump
    0.46
     jump
    0.42
    Jump
    0.41
    州
    0.41
     алуу
    0.41
     cro
    0.40
    square
    0.40
    Bor
    0.40
     चौक
    0.40
     jumper
    0.39
    Act Density 0.006%

    No Known Activations