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

    Neuronpedia

    INDEX
    Explanations

    parentheses or quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raphics
    -0.07
    _STYLE
    -0.07
     เค
    -0.06
    _BY
    -0.06
    анных
    -0.06
    雪
    -0.06
    ilece
    -0.06
    以前
    -0.06
    NetMessage
    -0.06
     Although
    -0.06
    POSITIVE LOGITS
     creditor
    0.06
    "';↵
    0.06
    (fabs
    0.06
     Sikh
    0.06
     incumbent
    0.06
     Specifications
    0.06
     Disclaimer
    0.06
    _requirements
    0.06
    】【
    0.06
     Continental
    0.06
    Act Density 0.070%

    No Known Activations