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

    Neuronpedia

    INDEX
    Explanations

    key value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    1.25
     Ju
    1.15
    ם
    1.13
    ্ড
    1.12
    idad
    1.11
    UAL
    1.07
    Wealth
    1.07
    WindowClass
    1.04
     zapatos
    1.03
    Ju
    1.02
    POSITIVE LOGITS
    hole
    1.58
    boards
    1.36
    chains
    1.26
    hö
    1.24
    cloak
    1.22
    phrase
    1.20
    aviti
    1.18
    ingi
    1.14
    frames
    1.11
    frameCount
    1.11
    Act Density 0.116%

    No Known Activations