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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tb
    -0.07
     anak
    -0.06
    (Sql
    -0.06
    쿠
    -0.06
    .addChild
    -0.06
     야
    -0.06
    meli
    -0.06
    界
    -0.06
    .character
    -0.06
    文化
    -0.06
    POSITIVE LOGITS
    ilendir
    0.07
     jylland
    0.07
     flaws
    0.07
     půl
    0.07
     ST
    0.07
     neust
    0.06
     rising
    0.06
     Pers
    0.06
     oath
    0.06
    lédl
    0.06
    Act Density 0.007%

    No Known Activations