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

    Neuronpedia

    INDEX
    Explanations

    introduction of examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    0.92
    u
    0.92
     Some
    0.82
    is
    0.78
    k
    0.76
    ら
    0.75
     )
    0.75
    于
    0.75
    na
    0.72
    ниці
    0.72
    POSITIVE LOGITS
    RVCT
    1.01
    <unused2144>
    0.94
    Methylsulfanyl
    0.92
    <unused2218>
    0.91
    FhirExtension
    0.90
    <unused1840>
    0.90
    <unused2139>
    0.90
    <unused282>
    0.89
    ylmethylsulfanyl
    0.89
    <unused2217>
    0.89
    Act Density 0.004%

    No Known Activations