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

    Neuronpedia

    INDEX
    Explanations

    attack against, correspondingly, by extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ancang
    0.39
     candidate
    0.38
     competition
    0.37
     svr
    0.36
     ጥቅም
    0.36
     ASCII
    0.36
     رح
    0.36
    ්ර
    0.36
    achery
    0.36
     फाइन
    0.36
    POSITIVE LOGITS
     correspondingly
    0.75
     proportionately
    0.70
    Corresponding
    0.70
     inherits
    0.69
    同步
    0.69
     ikut
    0.67
    跟着
    0.67
     Corresponding
    0.66
     indirectly
    0.64
    相应
    0.64
    Act Density 0.236%

    No Known Activations