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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     joy
    -0.09
     achten
    -0.09
     pravid
    -0.09
     unbearable
    -0.09
     meanwhile
    -0.09
     breakthroughs
    -0.08
    ऊ
    -0.08
    mort
    -0.08
     unnoticed
    -0.08
     agendas
    -0.08
    POSITIVE LOGITS
     reminiscent
    0.12
     essentially
    0.11
     Essentially
    0.10
     essentiellement
    0.10
     basically
    0.09
     довольно
    0.09
    Quadr
    0.08
     bedoeld
    0.08
     quadrant
    0.08
     khá
    0.08
    Act Density 0.098%

    No Known Activations