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

    Neuronpedia

    INDEX
    Explanations

    land and water

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Depth
    -0.07
     باد
    -0.06
    exp
    -0.06
    (enable
    -0.06
    leave
    -0.06
    理
    -0.06
    dragon
    -0.06
    얼
    -0.06
    igated
    -0.06
    -rec
    -0.06
    POSITIVE LOGITS
    istingu
    0.07
    μεν
    0.07
    ở
    0.07
    izzare
    0.06
     exclude
    0.06
     ^=
    0.06
     '"'
    0.06
    ダー
    0.06
     splitter
    0.06
    zM
    0.06
    Act Density 0.104%

    No Known Activations