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

    Neuronpedia

    INDEX
    Explanations

    G

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RLF
    -0.07
    ."&
    -0.07
    .dismiss
    -0.07
    =admin
    -0.06
    !=-
    -0.06
     userEmail
    -0.06
    Tai
    -0.06
    kish
    -0.06
    -vertical
    -0.06
    
    -0.06
    POSITIVE LOGITS
     lassen
    0.06
     представ
    0.06
    дер
    0.06
    _folders
    0.06
    створ
    0.06
    .).
    0.06
     Pharmac
    0.06
     Passing
    0.06
    arı
    0.06
     fic
    0.06
    Act Density 0.017%

    No Known Activations