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

    Neuronpedia

    INDEX
    Explanations

    search features and UI components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awesome
    0.48
    PIO
    0.43
    Awesome
    0.43
     awesome
    0.42
     repos
    0.42
    Repos
    0.41
    fontawesome
    0.41
    rape
    0.40
     Awesome
    0.39
     Wight
    0.39
    POSITIVE LOGITS
    Alg
    0.45
     Alg
    0.43
    San
    0.39
     Alph
    0.38
    四周
    0.38
    Statistics
    0.38
    igny
    0.37
     분명
    0.37
     Around
    0.36
    facet
    0.36
    Act Density 0.007%

    No Known Activations