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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дон
    0.54
    DRA
    0.45
    code
    0.44
     Code
    0.44
    f
    0.43
    нями
    0.42
    zá
    0.42
    éraires
    0.41
    вести
    0.40
     Thành
    0.40
    POSITIVE LOGITS
     ρ
    0.58
     μον
    0.54
     κ
    0.52
     increment
    0.52
     attrition
    0.52
     γλώ
    0.50
     sufficiency
    0.50
     rinsing
    0.49
     μην
    0.49
     wyja
    0.49
    Act Density 0.000%

    No Known Activations