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

    Neuronpedia

    INDEX
    Explanations

    contrasting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.87
    0.73
    2
    0.71
    1
    0.71
    ς
    0.70
     horaires
    0.70
    {
    0.70
     доступны
    0.69
     ligands
    0.69
    مان
    0.68
    POSITIVE LOGITS
    zelfde
    1.03
    Lastly
    0.91
     Isn
    0.87
     Wouldn
    0.85
     Questi
    0.84
     불구하고
    0.83
     perchè
    0.81
     però
    0.80
    にとっては
    0.80
    лизм
    0.79
    Act Density 0.028%

    No Known Activations