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

    Neuronpedia

    INDEX
    Explanations

    oldest surviving; history of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     formation
    0.58
     prone
    0.49
     propulsion
    0.49
    ed
    0.48
    aturally
    0.47
    ut
    0.46
    ague
    0.45
    paralleled
    0.45
     inflating
    0.44
     ಹೆಚ್ಚಿನ
    0.44
    POSITIVE LOGITS
    би
    0.62
    海上
    0.55
    MAN
    0.54
     econôm
    0.54
    ANCH
    0.52
     OTHER
    0.51
    ЗА
    0.50
    第
    0.50
    да
    0.50
    PLUS
    0.49
    Act Density 0.000%

    No Known Activations