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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bench
    -0.06
     Ips
    -0.06
    %%%%
    -0.06
     kijken
    -0.06
     endiş
    -0.06
     утвержд
    -0.06
    技
    -0.06
     deterior
    -0.06
     newX
    -0.06
    HEAD
    -0.06
    POSITIVE LOGITS
     substitutions
    0.06
     Unused
    0.06
     gun
    0.06
    /><
    0.06
    visions
    0.06
    structuring
    0.06
    _pdu
    0.06
    خرى
    0.06
    <Input
    0.06
     overview
    0.06
    Act Density 0.027%

    No Known Activations