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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	FOR
    -0.07
     정확
    -0.07
     auc
    -0.07
    リスト
    -0.06
    aukee
    -0.06
    epar
    -0.06
     приклад
    -0.06
    .Areas
    -0.06
    toBeFalsy
    -0.06
     ус
    -0.06
    POSITIVE LOGITS
    alach
    0.07
    (dir
    0.06
    _colour
    0.06
    -N
    0.06
     bunk
    0.06
    /community
    0.06
    _moves
    0.06
    три
    0.06
     원
    0.06
    Movement
    0.06
    Act Density 0.037%

    No Known Activations