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

    Neuronpedia

    INDEX
    Explanations

    company names and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     во
    0.60
    ів
    0.54
    azing
    0.54
     الت
    0.52
     réponse
    0.48
    绸
    0.47
     Toutes
    0.46
    剂
    0.46
     ар
    0.45
    ুল
    0.45
    POSITIVE LOGITS
    忶
    0.56
     dron
    0.53
    ເຮ
    0.51
    hehi
    0.50
    heira
    0.49
     harassed
    0.49
    ओके
    0.48
    ersiz
    0.47
    ernos
    0.47
    belly
    0.47
    Act Density 0.014%

    No Known Activations