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

    Neuronpedia

    INDEX
    Explanations

    Code/technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iera
    -0.07
    oven
    -0.07
    .throw
    -0.07
     Derek
    -0.07
    Ipv
    -0.06
    argins
    -0.06
     ip
    -0.06
    66
    -0.06
     CY
    -0.06
    chool
    -0.06
    POSITIVE LOGITS
    луг
    0.07
    isiert
    0.06
    _province
    0.06
     Void
    0.06
     vom
    0.06
    .Disclaimer
    0.06
    мом
    0.06
     optionally
    0.06
     userinfo
    0.06
     workings
    0.06
    Act Density 0.108%

    No Known Activations