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

    Neuronpedia

    INDEX
    Explanations

    "I know, I know" admissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     although
    0.52
     တော့
    0.42
    Although
    0.41
    although
    0.40
    虽然
    0.40
     certainly
    0.39
     experience
    0.38
     虽然
    0.38
    roffenen
    0.38
    不管
    0.38
    POSITIVE LOGITS
    Ideally
    0.45
    ぉ
    0.45
    oooo
    0.44
    !!!
    0.43
     sorry
    0.43
    !!!!
    0.42
    Yea
    0.41
    !!!"
    0.40
    Leaf
    0.40
     ironic
    0.40
    Act Density 0.007%

    No Known Activations