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

    Neuronpedia

    INDEX
    Explanations

    explores possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     execute
    0.54
    ív
    0.50
     执行
    0.49
     exorbit
    0.48
     didReceive
    0.47
     imshow
    0.47
     executable
    0.46
     istek
    0.46
     technische
    0.45
     vykon
    0.45
    POSITIVE LOGITS
    \
    0.51
    メタ
    0.48
    ก
    0.48
    Objet
    0.47
    タイム
    0.45
    Amino
    0.45
    ק
    0.45
    Emp
    0.44
    Studies
    0.44
    Catalogue
    0.44
    Act Density 0.000%

    No Known Activations