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

    Neuronpedia

    INDEX
    Explanations

    valves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canciones
    -0.08
    �
    -0.08
    ")(
    -0.08
     kohe
    -0.08
     бонус
    -0.08
     campañas
    -0.07
     memes
    -0.07
    朋友圈
    -0.07
     mandatory
    -0.07
     cohesion
    -0.07
    POSITIVE LOGITS
    olid
    0.09
     valve
    0.08
    UNDO
    0.08
     Undo
    0.08
     grau
    0.08
     hydraul
    0.08
     clog
    0.08
     clogged
    0.08
    Undo
    0.08
    -Out
    0.08
    Act Density 0.013%

    No Known Activations