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

    Neuronpedia

    INDEX
    Explanations

    .txt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Crear
    -0.07
     phase
    -0.07
    el
    -0.07
    .ads
    -0.06
     Election
    -0.06
    节
    -0.06
     cluster
    -0.06
    (action
    -0.06
     Sevilla
    -0.06
     OVERRIDE
    -0.06
    POSITIVE LOGITS
    Matt
    0.09
    tc
    0.08
     Matt
    0.08
    Capt
    0.07
     oč
    0.07
    XT
    0.07
    quate
    0.07
    atty
    0.07
    issued
    0.07
    URN
    0.07
    Act Density 0.009%

    No Known Activations