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

    Neuronpedia

    INDEX
    Explanations

    boot, lib, or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     między
    1.05
     между
    1.04
     जवाहर
    1.03
     Einfluss
    1.02
     Shifts
    1.01
     rozd
    1.01
     हमले
    1.00
     dala
    1.00
     zau
    0.96
     Coatings
    0.96
    POSITIVE LOGITS
    itud
    1.13
    f
    1.07
    mann
    1.04
    pdb
    1.04
    vana
    1.03
    MANN
    1.02
    ccak
    0.98
    ure
    0.98
    rera
    0.97
    vm
    0.97
    Act Density 0.000%

    No Known Activations