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

    Neuronpedia

    INDEX
    Explanations

    outstanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //.
    -0.07
     usually
    -0.07
     chances
    -0.07
     comparison
    -0.07
     eventual
    -0.07
    _hello
    -0.06
     ")");↵
    -0.06
    声を
    -0.06
     cosy
    -0.06
    _si
    -0.06
    POSITIVE LOGITS
     outstanding
    0.15
     Outstanding
    0.12
     upbeat
    0.07
     ettik
    0.07
    .oauth
    0.07
     upright
    0.07
     Stark
    0.07
     antioxidant
    0.07
     Bart
    0.07
     Stout
    0.07
    Act Density 0.005%

    No Known Activations