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

    Neuronpedia

    INDEX
    Explanations

    mountain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dia
    -0.08
     Friendship
    -0.07
    di
    -0.07
     via
    -0.07
    ռ
    -0.07
    временно
    -0.07
    phrase
    -0.07
    𝙪
    -0.06
     ri
    -0.06
    Lux
    -0.06
    POSITIVE LOGITS
    山
    0.09
     jav
    0.08
    しかも
    0.07
    evity
    0.07
     جهة
    0.07
    さん
    0.07
    鞍山
    0.07
    𣲗
    0.07
    .song
    0.07
    山坡
    0.07
    Act Density 0.016%

    No Known Activations