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

    Neuronpedia

    INDEX
    Explanations

    meta charset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FAS
    0.41
     FSC
    0.40
     SPA
    0.39
     Hr
    0.39
     бесе
    0.38
    尕
    0.37
     اث
    0.36
     uninsured
    0.36
    WriteStream
    0.36
     برق
    0.36
    POSITIVE LOGITS
    Billing
    0.42
    metall
    0.42
    Bur
    0.41
    Metal
    0.41
    âtel
    0.40
    metal
    0.39
     métall
    0.39
    urten
    0.39
    bur
    0.38
    Metall
    0.38
    Act Density 0.000%

    No Known Activations