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

    Neuronpedia

    INDEX
    Explanations

    navigation of spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Register
    -0.08
     unborn
    -0.07
    comfort
    -0.07
    Radius
    -0.07
    _days
    -0.07
     indir
    -0.07
     birth
    -0.07
     Behavior
    -0.07
     Mas
    -0.06
    过
    -0.06
    POSITIVE LOGITS
     xét
    0.07
    ccount
    0.06
     علاق
    0.06
    -json
    0.06
    was
    0.06
     krat
    0.06
     Redistributions
    0.06
     Hawth
    0.06
     період
    0.06
     包
    0.06
    Act Density 0.012%

    No Known Activations