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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     escalated
    -0.07
     Readers
    -0.07
    Patient
    -0.07
    (Location
    -0.06
    OWL
    -0.06
    感情
    -0.06
    .Geometry
    -0.06
     DISTRIBUT
    -0.06
    Bar
    -0.06
     THERE
    -0.06
    POSITIVE LOGITS
    .resume
    0.08
     PSI
    0.07
     ann
    0.06
    _prefs
    0.06
     simil
    0.06
     bạn
    0.06
    .scalar
    0.06
     tailor
    0.06
     sın
    0.06
    ，或
    0.06
    Act Density 0.032%

    No Known Activations