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

    Neuronpedia

    INDEX
    Explanations

    activity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    А
    -0.07
     Λ
    -0.06
    STATE
    -0.06
    _move
    -0.06
    /simple
    -0.06
    Icon
    -0.06
    وجه
    -0.06
    但
    -0.06
     EX
    -0.06
    	Array
    -0.06
    POSITIVE LOGITS
     thor
    0.07
    _;
    0.06
     Surf
    0.06
    ordial
    0.06
    ieg
    0.06
     plethora
    0.06
    piel
    0.06
     rhythm
    0.06
    _,↵
    0.06
     Trades
    0.06
    Act Density 0.035%

    No Known Activations