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

    Neuronpedia

    INDEX
    Explanations

    Consequence/result indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rua
    -0.07
    Harry
    -0.07
    ultural
    -0.07
    ista
    -0.07
     anger
    -0.07
     영어
    -0.07
    ani
    -0.07
    audio
    -0.07
    -million
    -0.07
    _budget
    -0.06
    POSITIVE LOGITS
     пад
    0.06
    (em
    0.06
    (KP
    0.06
     Robots
    0.06
     consortium
    0.06
    (sym
    0.05
    �
    0.05
    Cad
    0.05
     TextAlign
    0.05
     glBegin
    0.05
    Act Density 0.072%

    No Known Activations