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

    Neuronpedia

    INDEX
    Explanations

    .,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bread
    -0.07
    -brand
    -0.07
    TAIL
    -0.07
     layout
    -0.07
     layouts
    -0.06
    ブロ
    -0.06
    ética
    -0.06
    -header
    -0.06
    راف
    -0.06
    RN
    -0.06
    POSITIVE LOGITS
     elimin
    0.06
     ponds
    0.06
    .Pass
    0.06
     Cler
    0.06
     terminates
    0.06
    歯
    0.06
     Intern
    0.06
    ühl
    0.06
     بإ
    0.06
     เ
    0.06
    Act Density 0.010%

    No Known Activations