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

    Neuronpedia

    INDEX
    Explanations

    savedInstanceState

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FBSDKApp
    0.51
     grouse
    0.50
    ሯ
    0.50
     androidx
    0.49
    撚
    0.49
    PlayerSelector
    0.48
    NING
    0.47
     جھنڈ
    0.47
    NgramModel
    0.47
    midrule
    0.46
    POSITIVE LOGITS
     as
    0.58
    ஆக
    0.53
    ổ
    0.50
    ukum
    0.47
     Pet
    0.45
    অত
    0.44
     successfully
    0.44
     flu
    0.44
     namely
    0.43
    oč
    0.43
    Act Density 0.000%

    No Known Activations