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

    Neuronpedia

    INDEX
    Explanations

    proximity and closeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.21
    𝖗
    1.00
    is
    1.00
    дзен
    0.99
    प्रतिनि
    0.97
    কলকাতা
    0.95
    γραφ
    0.95
     Absatz
    0.95
     utterance
    0.93
    𝖒
    0.91
    POSITIVE LOGITS
    shoring
    1.15
     proximity
    1.02
    畿
    0.96
    nö
    0.94
     thereto
    0.92
    वर्ती
    0.92
    उदा
    0.91
    दर्शिता
    0.91
    RCT
    0.91
    िंग
    0.89
    Act Density 0.119%

    No Known Activations