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

    Neuronpedia

    INDEX
    Explanations

    listing examples and continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二是
    0.41
     two
    0.36
    two
    0.34
    ing
    0.34
    constrained
    0.32
    ary
    0.32
    at
    0.32
    ,
    0.32
     tetrahedral
    0.31
    al
    0.31
    POSITIVE LOGITS
     ইত্যাদি
    0.91
     etc
    0.88
    etc
    0.79
     etcétera
    0.78
     тощо
    0.78
    等等
    0.77
    などを
    0.74
     Etc
    0.73
     sebagainya
    0.70
     وغیرہ
    0.70
    Act Density 1.103%

    No Known Activations