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

    Neuronpedia

    INDEX
    Explanations

    Tumblr posts and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亗
    0.47
     ойнотуу
    0.44
    पेक्ष
    0.41
     ChatGPT
    0.41
    ˬ
    0.40
     збере
    0.39
     hamming
    0.39
    ाई
    0.38
    ariales
    0.38
    rivate
    0.38
    POSITIVE LOGITS
     Tumblr
    0.90
     tum
    0.83
    Tum
    0.83
    tumblr
    0.80
     Tum
    0.63
    tum
    0.57
     tumbler
    0.57
    tagged
    0.55
    Tag
    0.55
     fic
    0.54
    Act Density 0.010%

    No Known Activations