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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FRIEND
    -0.07
    anship
    -0.07
    stí
    -0.07
     insulated
    -0.07
    βε
    -0.07
    IRR
    -0.06
    рощ
    -0.06
     ود
    -0.06
     Politico
    -0.06
     FileReader
    -0.06
    POSITIVE LOGITS
    rending
    0.07
    Legal
    0.07
    .Percent
    0.06
     Phân
    0.06
    üss
    0.06
    ileges
    0.06
    /usr
    0.06
     hairs
    0.06
     keys
    0.06
    ین
    0.06
    Act Density 0.014%

    No Known Activations