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

    Neuronpedia

    INDEX
    Explanations

    layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampo
    -0.07
     Bew
    -0.07
    _dependencies
    -0.06
    .codigo
    -0.06
    ि�
    -0.06
     expressions
    -0.06
    olumbia
    -0.06
    亡
    -0.06
     stri
    -0.06
     Coord
    -0.06
    POSITIVE LOGITS
     手机
    0.07
     ||=
    0.07
     AssemblyCompany
    0.07
     Dixon
    0.06
     skilled
    0.06
     NFC
    0.06
    !)↵
    0.06
    anden
    0.06
    ,"↵
    0.06
     пози
    0.06
    Act Density 0.007%

    No Known Activations