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

    Neuronpedia

    INDEX
    Explanations

    Hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    採
    -0.07
     DPS
    -0.07
     CDC
    -0.07
     Shield
    -0.07
    ometimes
    -0.07
     evaluate
    -0.07
     można
    -0.07
     introduce
    -0.07
     Spawn
    -0.06
    LOOD
    -0.06
    POSITIVE LOGITS
    [length
    0.07
    ไฟล
    0.07
     lotion
    0.07
    redo
    0.07
    udp
    0.06
    [right
    0.06
    _HASH
    0.06
    <y
    0.06
    bringing
    0.06
     jsonString
    0.06
    Act Density 0.000%

    No Known Activations