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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slots
    -0.08
    Ан
    -0.07
    xygen
    -0.06
    _poly
    -0.06
    -Oct
    -0.06
     changed
    -0.06
    (relative
    -0.06
    alu
    -0.06
     liquids
    -0.06
    41
    -0.06
    POSITIVE LOGITS
    previous
    0.06
     등의
    0.06
    liğin
    0.06
     Johnny
    0.06
     tang
    0.06
     Dispatch
    0.06
     Recorder
    0.06
     Wr
    0.06
     香港
    0.06
     trenches
    0.06
    Act Density 0.000%

    No Known Activations