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

    Neuronpedia

    INDEX
    Explanations

    lists ending with conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contrace
    0.52
     Sith
    0.51
     theolog
    0.50
     gide
    0.49
    ร์
    0.49
    ต์
    0.49
     hypersurfaces
    0.48
     birefringence
    0.48
     infert
    0.48
     locul
    0.48
    POSITIVE LOGITS
    mov
    0.57
    uh
    0.50
    loe
    0.49
    aisseur
    0.49
    modal
    0.48
    exus
    0.48
    U
    0.47
    HC
    0.47
    man
    0.46
    uch
    0.45
    Act Density 0.000%

    No Known Activations