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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LT
    -0.06
    ばかり
    -0.06
    sher
    -0.06
    CEE
    -0.06
    EEE
    -0.06
    .std
    -0.06
    ячи
    -0.06
    参照
    -0.06
     traceback
    -0.06
     pew
    -0.06
    POSITIVE LOGITS
    	video
    0.08
     motion
    0.07
     preco
    0.07
     chiefs
    0.07
     Land
    0.06
    Definitions
    0.06
    Выб
    0.06
     conjunto
    0.06
     stating
    0.06
    ronic
    0.06
    Act Density 0.026%

    No Known Activations