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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    charm
    -0.07
    ,(
    -0.06
     Mutable
    -0.06
     alguna
    -0.06
     velké
    -0.06
     souvenir
    -0.06
    ":[-
    -0.06
     salud
    -0.06
     Pall
    -0.06
     Solo
    -0.06
    POSITIVE LOGITS
     стало
    0.08
     Carry
    0.08
     Brother
    0.07
    .ServletException
    0.07
    committed
    0.07
    .д
    0.07
    asion
    0.07
    ifications
    0.06
     foreigners
    0.06
     uncomment
    0.06
    Act Density 0.012%

    No Known Activations