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

    Neuronpedia

    INDEX
    Explanations

    code snippets/technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crypto
    -0.07
     cops
    -0.07
    	or
    -0.07
    (axis
    -0.07
     ем
    -0.07
    ौ
    -0.07
    igar
    -0.06
    osta
    -0.06
    _delete
    -0.06
     letto
    -0.06
    POSITIVE LOGITS
     december
    0.07
     roční
    0.07
     países
    0.06
     ideally
    0.06
     Buster
    0.06
    imdi
    0.06
    """
    0.06
     صرف
    0.06
    řed
    0.06
    Feat
    0.06
    Act Density 0.001%

    No Known Activations