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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卜
    -0.07
    ausible
    -0.07
    "On
    -0.07
    gard
    -0.07
    春节期间
    -0.07
    isé
    -0.07
     HBO
    -0.06
    반
    -0.06
    �
    -0.06
    ib
    -0.06
    POSITIVE LOGITS
    .Employee
    0.08
     Paulo
    0.08
    flamm
    0.07
     tranqu
    0.07
    -object
    0.07
    registered
    0.07
    .accessToken
    0.07
     profit
    0.07
    CPU
    0.07
    Thickness
    0.07
    Act Density 0.001%

    No Known Activations