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

    Neuronpedia

    INDEX
    Explanations

    identifying units or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Belief
    0.47
    İK
    0.47
    วม
    0.42
    oxel
    0.42
     Organization
    0.41
    İN
    0.41
    ah
    0.41
    o
    0.40
    念
    0.40
    ্ল
    0.40
    POSITIVE LOGITS
     risiko
    0.50
    قافة
    0.48
    冊
    0.47
     kunder
    0.45
     marshall
    0.45
     sheaves
    0.45
     ponto
    0.45
    ตู
    0.45
     partager
    0.44
     впоследствии
    0.44
    Act Density 0.000%

    No Known Activations