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

    Neuronpedia

    INDEX
    Explanations

    /min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocab
    -0.07
    릿
    -0.07
     nota
    -0.07
     ql
    -0.07
     lạ
    -0.06
     Teil
    -0.06
    ounced
    -0.06
    .Encode
    -0.06
     Wel
    -0.06
     Necessary
    -0.06
    POSITIVE LOGITS
    ½
    0.07
     Tristan
    0.06
     honorary
    0.06
     Nay
    0.06
    -pocket
    0.06
    eless
    0.06
    /min
    0.06
    chwitz
    0.06
     insecurity
    0.06
    getResult
    0.06
    Act Density 0.005%

    No Known Activations