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

    Neuronpedia

    INDEX
    Explanations

    funnily, !! , DA sounds

    np_acts-logits-general · gemini-2.5-flash-lite

    placeholders or markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нков
    0.71
    Ꮸ
    0.70
    에서도
    0.66
    왤
    0.65
    ,|\
    0.64
    МИ
    0.63
    ALWAYS
    0.63
    ጥረ
    0.61
    다면
    0.61
    ,((
    0.61
    POSITIVE LOGITS
    ling
    0.88
    son
    0.85
    ando
    0.83
    um
    0.80
    nes
    0.77
    ने
    0.76
    ife
    0.75
    ship
    0.74
    ros
    0.73
    ری
    0.73
    Act Density 0.158%

    No Known Activations