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

    Neuronpedia

    INDEX
    Explanations

    output

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VERY
    -0.08
     mend
    -0.07
    itational
    -0.07
    _SELECTED
    -0.07
    Ҁ
    -0.07
     несколько
    -0.07
    _THRESHOLD
    -0.07
    enson
    -0.07
     Disaster
    -0.06
     dont
    -0.06
    POSITIVE LOGITS
     thuisontvangst
    0.08
    留在
    0.07
    continued
    0.07
    ‗
    0.07
    댑
    0.07
     "~
    0.06
    ᩁ
    0.06
     productList
    0.06
    vision
    0.06
     замеча
    0.06
    Act Density 0.092%

    No Known Activations