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
     lucru
    -0.52
     appartient
    -0.49
     betyd
    -0.47
     altre
    -0.47
     eller
    -0.46
     rapides
    -0.46
    began
    -0.45
     comenzaron
    -0.44
     tölt
    -0.44
    名叫
    -0.44
    POSITIVE LOGITS
    )"),
    0.84
    |}{$
    0.82
    ]."
    0.78
    )”.
    0.78
    ]`
    0.77
    wiſe
    0.77
    ″]
    0.76
     }}$}
    0.76
    PhysRevLett
    0.76
    '".
    0.75
    Act Density 0.214%

    No Known Activations