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

    Neuronpedia

    INDEX
    Explanations

    clickbait headlines with emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பின்ன
    0.41
    ceptor
    0.40
    დომ
    0.40
    consuming
    0.39
    ulfate
    0.39
     ডকুম
    0.38
     powders
    0.38
    蒇
    0.38
     partur
    0.38
     উপরে
    0.37
    POSITIVE LOGITS
     Yoon
    0.49
     Wow
    0.46
    Yay
    0.46
     wow
    0.44
    yay
    0.43
     Yay
    0.42
    <start_of_image>
    0.42
     yay
    0.41
    wow
    0.41
    Biden
    0.41
    Act Density 0.001%

    No Known Activations