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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    origin
    -0.07
    *A
    -0.07
    definitions
    -0.06
    node
    -0.06
    abbit
    -0.06
     grace
    -0.06
    pearance
    -0.06
    inha
    -0.06
    conto
    -0.06
     Serious
    -0.06
    POSITIVE LOGITS
    Displays
    0.08
     resto
    0.07
     ganze
    0.07
    _DX
    0.07
    사회
    0.06
    amil
    0.06
     Tottenham
    0.06
    ้ไข
    0.06
    DidEnter
    0.06
    +/
    0.06
    Act Density 0.299%

    No Known Activations