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

    Neuronpedia

    INDEX
    Explanations

    scientific publication references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nob
    -0.06
     답
    -0.06
    Locker
    -0.06
    -clock
    -0.06
     Alto
    -0.06
     transit
    -0.06
    odia
    -0.06
     Dahl
    -0.06
    WEST
    -0.05
    (Y
    -0.05
    POSITIVE LOGITS
    συ
    0.07
     fiery
    0.07
     userdata
    0.07
    emento
    0.07
    .↵
    0.07
     toasted
    0.07
     memories
    0.07
     nová
    0.07
    ewing
    0.07
    0.06
    Act Density 0.002%

    No Known Activations