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

    Neuronpedia

    INDEX
    Explanations

    ./ followed by a command or file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     challenge
    0.50
     메
    0.50
     media
    0.50
    시
    0.49
    of
    0.49
     program
    0.49
     discard
    0.47
     관리
    0.47
     de
    0.46
     OF
    0.46
    POSITIVE LOGITS
    ي
    0.55
    其他
    0.49
    કમાં
    0.48
    gleichen
    0.48
    يق
    0.46
    ವಾಸ
    0.46
     ausdr
    0.46
    м
    0.46
    .​​
    0.45
    حياته
    0.45
    Act Density 0.024%

    No Known Activations