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

    Neuronpedia

    INDEX
    Explanations

    programming input/output streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nent
    0.39
    ن
    0.38
    value
    0.37
    taker
    0.37
    istream
    0.35
     "");
    0.34
    roduct
    0.34
     Zuh
    0.34
    露
    0.34
     openly
    0.34
    POSITIVE LOGITS
    돛
    0.42
    髂
    0.41
    ₁(
    0.39
     американский
    0.39
     Watercolour
    0.39
    ₂(
    0.38
    CSharp
    0.38
    Alright
    0.38
    ρε
    0.38
     ricos
    0.38
    Act Density 0.004%

    No Known Activations