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

    Neuronpedia

    INDEX
    Explanations

    Brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Place
    -0.08
     Ave
    -0.08
     schöne
    -0.07
    .xx
    -0.07
    nung
    -0.07
     severely
    -0.07
     Posted
    -0.07
    verse
    -0.07
    นำเสนอ
    -0.07
     Aff
    -0.07
    POSITIVE LOGITS
    영
    0.07
    栗
    0.07
    Volt
    0.07
    getContext
    0.07
    (type
    0.07
     пря
    0.07
     flawless
    0.07
    履行
    0.07
    Scripts
    0.07
     communism
    0.06
    Act Density 0.011%

    No Known Activations