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

    Neuronpedia

    INDEX
    Explanations

    text formatting and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jet
    0.43
     Jet
    0.39
    Jet
    0.38
     juice
    0.38
     vans
    0.37
     passenger
    0.35
     reps
    0.35
     satellite
    0.35
     jets
    0.34
     الي
    0.34
    POSITIVE LOGITS
    stability
    0.57
    不安定
    0.57
    稳定性
    0.56
     안정
    0.56
    不稳定
    0.56
    安定
    0.54
    Stability
    0.54
     unstable
    0.53
    穩定
    0.53
    稳定
    0.52
    Act Density 0.000%

    No Known Activations