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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FACE
    -0.07
     các
    -0.06
     []*
    -0.06
    softmax
    -0.06
     hardwood
    -0.06
    桐
    -0.06
     Gib
    -0.06
     StatefulWidget
    -0.06
    .make
    -0.06
    cobra
    -0.05
    POSITIVE LOGITS
    xx
    0.08
     ülk
    0.07
    )}}"
    0.07
    .rotate
    0.07
    ráv
    0.07
    _bins
    0.07
    ron
    0.07
    \xf
    0.07
    .sal
    0.07
    _dm
    0.07
    Act Density 0.001%

    No Known Activations