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

    Neuronpedia

    INDEX
    Explanations

    Second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рова
    -0.07
     radar
    -0.07
    ulet
    -0.06
     Collins
    -0.06
     vergi
    -0.06
     withdrawal
    -0.06
     krat
    -0.06
     Carrie
    -0.06
     dong
    -0.06
    YOU
    -0.06
    POSITIVE LOGITS
    Tp
    0.08
    بعد
    0.08
    �
    0.07
    แปลง
    0.07
    .nextElement
    0.06
     routines
    0.06
     blamed
    0.06
     bonne
    0.06
    ("%
    0.06
    以外
    0.06
    Act Density 0.008%

    No Known Activations