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

    Neuronpedia

    INDEX
    Explanations

    code and licensing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wang
    -0.07
     baja
    -0.06
     закуп
    -0.06
     sigu
    -0.06
    _t
    -0.06
     STACK
    -0.06
    _outputs
    -0.06
    publish
    -0.06
     Ukraj
    -0.06
     kd
    -0.06
    POSITIVE LOGITS
    .Ext
    0.06
    ==============↵
    0.06
     ))↵↵
    0.06
    　
    0.06
     "]");↵
    0.06
    Raises
    0.06
    |{↵
    0.06
    umno
    0.06
     Overflow
    0.06
    --------------------------------------------------------------------------↵
    0.06
    Act Density 0.022%

    No Known Activations