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

    Neuronpedia

    INDEX
    Explanations

    Marketing/Community building texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compact
    -0.07
     revolt
    -0.06
     fol
    -0.06
     Bread
    -0.06
    iqué
    -0.06
    SES
    -0.06
    تبة
    -0.06
    +offset
    -0.06
     Clubs
    -0.06
     Official
    -0.06
    POSITIVE LOGITS
    宁
    0.08
    -В
    0.07
     piss
    0.07
    ').'</
    0.07
     quản
    0.06
     "')
    0.06
     Naming
    0.06
     yc
    0.06
    ')}}"></
    0.06
    ़ों
    0.06
    Act Density 0.023%

    No Known Activations