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

    Neuronpedia

    INDEX
    Explanations

    bridge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hemen
    -0.08
    etails
    -0.08
     Expand
    -0.08
     दुनिया
    -0.08
    queeze
    -0.08
     deuda
    -0.08
     entitlement
    -0.08
     Chartered
    -0.08
     mundo
    -0.08
     tune
    -0.08
    POSITIVE LOGITS
    组合
    0.09
     symmetry
    0.08
     damaging
    0.08
    _DIG
    0.08
     combustível
    0.08
     beschäd
    0.08
    Ranking
    0.07
     symmetrical
    0.07
     Fuel
    0.07
    Sri
    0.07
    Act Density 0.002%

    No Known Activations