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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lients
    -0.07
     PST
    -0.07
    do
    -0.07
     included
    -0.07
     pinned
    -0.06
     zahl
    -0.06
     mê
    -0.06
     kır
    -0.06
    confirm
    -0.06
     попыт
    -0.06
    POSITIVE LOGITS
     qualitative
    0.06
    。一
    0.06
     tn
    0.06
     gardening
    0.06
     thứ
    0.06
    BeforeEach
    0.06
     olumlu
    0.06
    <My
    0.06
    Biz
    0.06
    env
    0.06
    Act Density 0.001%

    No Known Activations