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
    .mov
    -0.07
    ep
    -0.07
    放
    -0.07
    endedor
    -0.07
    renderer
    -0.07
    chair
    -0.06
     collectionView
    -0.06
    centre
    -0.06
    rad
    -0.06
    енка
    -0.06
    POSITIVE LOGITS
     OF
    0.07
    ocê
    0.06
     تصم
    0.06
    	TRACE
    0.06
     βρί
    0.06
     estilo
    0.06
    _BIT
    0.06
     символ
    0.06
     이것
    0.06
     disadvantage
    0.06
    Act Density 0.057%

    No Known Activations