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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Math
    -0.08
    .trailing
    -0.07
    _ev
    -0.07
    .Loader
    -0.07
     muj
    -0.07
    (newUser
    -0.07
    -exec
    -0.07
     disadv
    -0.07
    önü
    -0.07
    .memo
    -0.07
    POSITIVE LOGITS
     segments
    0.07
    rega
    0.07
     ferm
    0.07
    因为我们
    0.06
     Dor
    0.06
     walking
    0.06
     영
    0.06
    极
    0.06
    퓁
    0.06
     sort
    0.06
    Act Density 0.001%

    No Known Activations