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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾਬ
    0.55
    ة
    0.50
    樖
    0.49
    ライダー
    0.46
    ूस
    0.46
    ُول
    0.46
    ೌ
    0.45
    حة
    0.45
    🇻
    0.45
    దు
    0.44
    POSITIVE LOGITS
    Build
    0.55
     Perks
    0.55
     can
    0.55
    Feature
    0.54
     Pattes
    0.53
    ica
    0.52
    Coat
    0.51
     Inter
    0.51
    Criteria
    0.51
    round
    0.50
    Act Density 0.000%

    No Known Activations