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

    Neuronpedia

    INDEX
    Explanations

    reduce

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =""/>↵
    -0.07
     telefono
    -0.07
     Completed
    -0.07
     crossover
    -0.07
     זמן
    -0.06
     kidnapping
    -0.06
     cigarettes
    -0.06
    ")));
↵
    -0.06
    ↵			↵
    -0.06
    楽し�
    -0.06
    POSITIVE LOGITS
     Staff
    0.07
     Shut
    0.07
     do
    0.06
    ms
    0.06
     Polynomial
    0.06
    壁
    0.06
    (buffer
    0.06
     Sous
    0.06
    ustr
    0.06
    给
    0.06
    Act Density 0.004%

    No Known Activations