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

    Neuronpedia

    INDEX
    Explanations

    ing/ed suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lars
    -0.07
     ド
    -0.07
    unknown
    -0.06
     OLD
    -0.06
     inclus
    -0.06
    LOPT
    -0.06
    Attachment
    -0.06
    makers
    -0.06
     Kl
    -0.06
    数字
    -0.06
    POSITIVE LOGITS
     watering
    0.18
     brown
    0.07
    .writeFileSync
    0.07
    .hover
    0.06
     jmen
    0.06
    _inches
    0.06
     policing
    0.06
     hacking
    0.06
     Brown
    0.06
     filing
    0.06
    Act Density 0.003%

    No Known Activations