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

    Neuronpedia

    INDEX
    Explanations

    ING and ERS suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    의
    -0.07
     》
    -0.06
     d
    -0.06
     başlam
    -0.06
     newY
    -0.06
     Of
    -0.06
     IDb
    -0.06
     cocktails
    -0.06
    :key
    -0.06
    Donald
    -0.06
    POSITIVE LOGITS
    ed
    0.07
    ORIZONTAL
    0.07
    ughters
    0.07
    indrical
    0.07
    postgres
    0.07
    ids
    0.07
    ing
    0.07
    ensagem
    0.07
    oğunluk
    0.07
    xito
    0.07
    Act Density 4.687%

    No Known Activations