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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     выдел
    -0.07
    onomous
    -0.06
    čel
    -0.06
    cock
    -0.06
     PROFITS
    -0.06
     jusqu
    -0.06
    HexString
    -0.06
    žít
    -0.06
     drip
    -0.06
    ラス
    -0.06
    POSITIVE LOGITS
     T
    0.10
    T
    0.10
    	t
    0.09
    .T
    0.08
    -t
    0.08
    t
    0.08
    ,t
    0.08
     A
    0.08
     t
    0.08
    -T
    0.08
    Act Density 0.114%

    No Known Activations