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

    Neuronpedia

    INDEX
    Explanations

    death/unconsciousness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -U
    -0.08
    .Lookup
    -0.07
    вин
    -0.07
    елів
    -0.07
    alen
    -0.06
    Ｂ
    -0.06
    pheres
    -0.06
     undecided
    -0.06
    ิดต
    -0.06
    isí
    -0.06
    POSITIVE LOGITS
     Thurs
    0.07
     참고
    0.06
     projectiles
    0.06
    ?',↵
    0.06
     swal
    0.06
    shots
    0.06
     bdsm
    0.06
    populate
    0.06
     اق
    0.06
    iname
    0.06
    Act Density 0.014%

    No Known Activations