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

    Neuronpedia

    INDEX
    Explanations

    Consultancy Services and angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    螯
    1.40
     empêcher
    1.36
    뿡
    1.35
    ͗
    1.33
    ू
    1.32
    ுக
    1.30
    ότερα
    1.29
    1.28
    𝙨
    1.28
     envoy
    1.27
    POSITIVE LOGITS
    aths
    1.18
     piet
    1.08
     że
    1.03
     wow
    0.99
     sli
    0.96
    드
    0.96
    𝗱
    0.96
     bahan
    0.94
     thirds
    0.94
     mild
    0.94
    Act Density 0.000%

    No Known Activations