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

    Neuronpedia

    INDEX
    Explanations

    scale and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     designer
    0.48
     devoted
    0.47
     torrential
    0.46
     પૂ
    0.44
     vegg
    0.44
     furry
    0.44
     designers
    0.41
    耿
    0.41
     called
    0.41
     fringilla
    0.41
    POSITIVE LOGITS
    omer
    0.41
    製品
    0.38
    同士
    0.38
     Firmware
    0.38
     alkalinity
    0.37
     Corning
    0.36
     FISHER
    0.36
     إلي
    0.36
     삭제
    0.35
    omers
    0.35
    Act Density 0.001%

    No Known Activations