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

    Neuronpedia

    INDEX
    Explanations

    chess king

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ESR
    0.44
     Fac
    0.41
    ితీ
    0.40
     Photos
    0.39
     Hooks
    0.39
     dzień
    0.39
     తేదీ
    0.39
     Screenshots
    0.39
     Hodgson
    0.38
    েম্বরে
    0.38
    POSITIVE LOGITS
    \!
    0.39
    {\
    0.38
     campaigned
    0.37
    判
    0.37
    T
    0.37
    éc
    0.36
    Wil
    0.35
     occupants
    0.35
     provision
    0.35
     repos
    0.35
    Act Density 0.001%

    No Known Activations