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

    Neuronpedia

    INDEX
    Explanations

    religion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特殊
    -0.07
    .cent
    -0.06
     unidades
    -0.06
     terminator
    -0.06
    tridges
    -0.06
    .resize
    -0.06
    .transition
    -0.06
    stan
    -0.06
     التس
    -0.06
     vomiting
    -0.06
    POSITIVE LOGITS
    ....
    0.06
     ment
    0.06
     مر
    0.06
    _Y
    0.06
    _er
    0.06
    	be
    0.06
     abusing
    0.06
     sadly
    0.06
    ��
    0.06
     four
    0.06
    Act Density 0.003%

    No Known Activations