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

    Neuronpedia

    INDEX
    Explanations

    step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    M
    0.59
     eines
    0.57
    N
    0.56
    C
    0.54
     banknotes
    0.53
     endpoints
    0.53
     quantify
    0.52
     three
    0.50
     ports
    0.49
     axons
    0.49
    POSITIVE LOGITS
     తనకు
    0.52
     различ
    0.51
    abhavena
    0.49
    ARIO
    0.46
    ilà
    0.46
    atthena
    0.46
    严
    0.46
    əsi
    0.46
     这
    0.45
     没有
    0.45
    Act Density 0.035%

    No Known Activations