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

    Neuronpedia

    INDEX
    Explanations

    creation, purpose, or version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nek
    0.47
    న్నా
    0.45
    ద
    0.44
     rebuilding
    0.43
     ANT
    0.43
    旪
    0.43
     instru
    0.43
     Montessori
    0.42
    ziger
    0.42
     Anaconda
    0.42
    POSITIVE LOGITS
    ቶችን
    0.48
    ulação
    0.47
    らかな
    0.47
    isValid
    0.45
     isValid
    0.45
    ління
    0.43
    퍄
    0.43
     commencé
    0.42
     pequeña
    0.42
     hätte
    0.42
    Act Density 0.004%

    No Known Activations