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

    Neuronpedia

    INDEX
    Explanations

    SQL and Python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TNumber
    0.40
    棹
    0.39
    ')"
    0.38
    翳
    0.38
    ্লিকেশন
    0.37
    )">
    0.37
    BackendAuth
    0.37
     couldnt
    0.36
     मानदंड
    0.36
     നമ്മ
    0.36
    POSITIVE LOGITS
    pre
    0.39
    so
    0.38
    ᅲ
    0.38
    quant
    0.37
    um
    0.36
     t
    0.36
    pure
    0.35
    di
    0.34
     Mor
    0.34
    eria
    0.34
    Act Density 0.004%

    No Known Activations