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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overlaps
    -0.07
     mole
    -0.06
     เก
    -0.06
    operator
    -0.06
    /tmp
    -0.06
     tempfile
    -0.06
     Fate
    -0.06
    一直
    -0.06
    clientes
    -0.06
     humanitarian
    -0.06
    POSITIVE LOGITS
    Rent
    0.07
    執
    0.06
    INESS
    0.06
    	cb
    0.06
    azon
    0.06
    _pkt
    0.06
     درون
    0.06
    _MESH
    0.06
     çöz
    0.06
     sheds
    0.06
    Act Density 0.279%

    No Known Activations