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

    Neuronpedia

    INDEX
    Explanations

    weather forecast details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     每个
    0.41
    ToInt
    0.39
     "=",
    0.38
     ionization
    0.37
    tgts
    0.36
    InputDialog
    0.36
    删
    0.36
    宍
    0.35
     Combien
    0.35
    NOWLEDG
    0.35
    POSITIVE LOGITS
     Overall
    0.69
    Overall
    0.61
    overall
    0.59
     mild
    0.58
    latest
    0.54
     overall
    0.54
     latest
    0.53
     Lite
    0.53
    expect
    0.52
     Latest
    0.52
    Act Density 0.017%

    No Known Activations