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

    Neuronpedia

    INDEX
    Explanations

    Sure, here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adecimal
    0.39
     задума
    0.37
    BANNER
    0.36
    학년
    0.35
    围绕
    0.35
    奋
    0.35
     resultContent
    0.34
    苒
    0.34
    努力
    0.34
    頑張
    0.34
    POSITIVE LOGITS
    Sure
    0.63
     Sure
    0.60
     sure
    0.54
    footed
    0.47
     enough
    0.46
    NV
    0.43
     Parallel
    0.42
     NV
    0.40
     thing
    0.40
    ーツ
    0.39
    Act Density 0.001%

    No Known Activations