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

    Neuronpedia

    INDEX
    Explanations

    json format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spin
    0.90
    費
    0.86
    嵘
    0.82
     Spins
    0.82
    bellar
    0.79
    खार
    0.77
    iramente
    0.77
    werden
    0.77
    ICHIGAN
    0.76
    ウザ
    0.76
    POSITIVE LOGITS
    webtoken
    1.37
    JSON
    1.20
     JSON
    1.18
    NewDecoder
    1.03
     nameWithOwner
    1.03
    rpc
    1.02
     json
    0.99
    json
    0.99
    Ⓒ
    0.99
     jq
    0.98
    Act Density 0.075%

    No Known Activations