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

    Neuronpedia

    INDEX
    Explanations

    html divs and buttons with attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bottomLeft
    0.24
    érant
    0.23
    വർ
    0.22
     khổ
    0.22
    渡し
    0.22
     ننوت
    0.21
    藪
    0.21
     illet
    0.21
     immunoblot
    0.21
    栉
    0.21
    POSITIVE LOGITS
     id
    0.37
    bind
    0.25
     bind
    0.24
     Net
    0.24
    att
    0.24
    my
    0.23
     Id
    0.23
    me
    0.23
     Alt
    0.22
    id
    0.22
    Act Density 0.006%

    No Known Activations