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

    Neuronpedia

    INDEX
    Explanations

    say @

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avic
    -0.07
     ServletException
    -0.07
    -vous
    -0.07
     Buffett
    -0.06
     impass
    -0.06
    찿
    -0.06
    ifr
    -0.06
    🧢
    -0.06
    ℏ
    -0.06
    preload
    -0.06
    POSITIVE LOGITS
    이라고
    0.07
    十九大
    0.07
    ("↵
    0.07
     donors
    0.07
    '");↵
    0.06
    Clients
    0.06
    越来越高
    0.06
    细节
    0.06
     patrol
    0.06
    規
    0.06
    Act Density 0.004%

    No Known Activations