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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icz
    -0.07
    acoes
    -0.06
    ]:
↵
    -0.06
    ataloader
    -0.06
    ECH
    -0.06
    ـل
    -0.06
    '>"
    -0.06
    널
    -0.06
    SG
    -0.06
    cir
    -0.06
    POSITIVE LOGITS
     bidi
    0.07
     remind
    0.07
     vý
    0.07
    /embed
    0.06
     ihnen
    0.06
    _AUD
    0.06
     patiently
    0.06
     aligned
    0.06
    {})
    0.06
    찬
    0.06
    Act Density 0.012%

    No Known Activations