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

    Neuronpedia

    INDEX
    Explanations

    show business

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hand
    -0.07
     adapt
    -0.06
    /weather
    -0.06
    guards
    -0.06
    мы
    -0.06
    CERT
    -0.06
    zip
    -0.06
    Quality
    -0.06
    variant
    -0.06
     ARM
    -0.06
    POSITIVE LOGITS
     voir
    0.06
     UNIVERSITY
    0.06
    澳
    0.06
     budete
    0.06
     대학
    0.06
     postId
    0.06
     //~
    0.06
     FAILED
    0.06
    (msg
    0.06
     거야
    0.06
    Act Density 0.182%

    No Known Activations