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

    Neuronpedia

    INDEX
    Explanations

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     so
    0.61
     berharap
    0.61
     all
    0.60
     guarantees
    0.59
     just
    0.58
     partner
    0.58
     lids
    0.57
     dominions
    0.57
     partners
    0.57
     incompar
    0.56
    POSITIVE LOGITS
    𝗔
    0.60
    ሔ
    0.54
    𝗥
    0.54
    𝗖
    0.53
    িলিয়া
    0.52
    𝗘
    0.52
    𝗨
    0.52
    𝗜
    0.51
    propan
    0.50
     PartialEq
    0.50
    Act Density 0.000%

    No Known Activations