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

    Neuronpedia

    INDEX
    Explanations

    riddles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    berger
    -0.07
    ึง
    -0.07
    _table
    -0.07
    できない
    -0.06
     Rotterdam
    -0.06
    ği
    -0.06
    isas
    -0.06
    แห
    -0.06
    形
    -0.06
    _traj
    -0.06
    POSITIVE LOGITS
     BorderRadius
    0.07
     Approx
    0.07
    andi
    0.06
     ','.
    0.06
     distinguish
    0.06
    	sum
    0.06
     phy
    0.06
    "fmt
    0.06
     Liberation
    0.06
    LOGGER
    0.06
    Act Density 0.138%

    No Known Activations