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

    Neuronpedia

    INDEX
    Explanations

    past conversations, while driving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bin
    0.47
    sub
    0.46
    chemin
    0.45
    next
    0.45
    bin
    0.45
     ellos
    0.45
    Continu
    0.44
     вони
    0.44
    バ
    0.44
    chester
    0.44
    POSITIVE LOGITS
     Scoring
    0.44
    误差
    0.44
     Aids
    0.41
     Differential
    0.40
    卫
    0.40
     Unwrap
    0.40
     junit
    0.40
    ViewHolder
    0.39
    几种
    0.39
     Mathematical
    0.38
    Act Density 0.012%

    No Known Activations