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

    Neuronpedia

    INDEX
    Explanations

    greetings and friendly openers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     axiomatic
    0.44
     blame
    0.40
    Thoreau
    0.40
     alcoholism
    0.39
    事實
    0.37
     dementia
    0.37
    nonsense
    0.37
     egregious
    0.36
     Frankly
    0.36
    idlertid
    0.36
    POSITIVE LOGITS
     awesome
    0.71
     Awesome
    0.59
     Hey
    0.57
    Awesome
    0.53
     hey
    0.51
    awesome
    0.51
    めっちゃ
    0.50
     hi
    0.49
     Hi
    0.49
     hola
    0.48
    Act Density 0.001%

    No Known Activations