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

    Neuronpedia

    INDEX
    Explanations

    Microsoft Visual C++ code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _STAT
    -0.06
     Sr
    -0.06
    BY
    -0.06
     wise
    -0.06
    action
    -0.06
     AVAILABLE
    -0.06
    Unsigned
    -0.06
    Saga
    -0.06
    .st
    -0.06
     masse
    -0.06
    POSITIVE LOGITS
     ami
    0.08
    comput
    0.07
     PF
    0.07
     début
    0.06
    (Have
    0.06
    rique
    0.06
    rocket
    0.06
    "default
    0.06
    ameron
    0.06
     رح
    0.06
    Act Density 0.005%

    No Known Activations