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

    Neuronpedia

    INDEX
    Explanations

    acronyms for conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unya
    0.42
    iniu
    0.40
    щиков
    0.39
    ierte
    0.39
    liquer
    0.39
    inalis
    0.39
    ikli
    0.38
    गाने
    0.38
     sata
    0.37
    lysninger
    0.37
    POSITIVE LOGITS
     LinkedIn
    0.57
     YouTube
    0.52
     Blog
    0.49
    Blog
    0.48
     Consultado
    0.48
    LinkedIn
    0.47
    YouTube
    0.47
     Vimeo
    0.47
     Pinterest
    0.45
     Flickr
    0.44
    Act Density 0.095%

    No Known Activations