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

    Neuronpedia

    INDEX
    Explanations

    unorganized text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McGu
    -0.06
     Pant
    -0.06
     ConfigurationManager
    -0.06
    toupper
    -0.06
     температу
    -0.06
     Mines
    -0.06
    RG
    -0.06
     Mum
    -0.06
     Kč
    -0.06
     '^
    -0.06
    POSITIVE LOGITS
    _return
    0.07
     Readers
    0.07
    ’nin
    0.07
    ーティ
    0.07
    _tuple
    0.07
     cook
    0.06
     unicorn
    0.06
     Cookie
    0.06
    los
    0.06
     ABC
    0.06
    Act Density 0.079%

    No Known Activations