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

    Neuronpedia

    INDEX
    Explanations

    achieve or undergo outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rid
    0.47
     acquaint
    0.44
     vraiment
    0.43
     mileage
    0.42
     tired
    0.41
     acquainted
    0.41
     odometer
    0.41
     dirty
    0.41
     confid
    0.41
     davvero
    0.41
    POSITIVE LOGITS
     Any
    0.45
     RESERVE
    0.45
     berücksichtigt
    0.45
    হাট
    0.43
    KEYS
    0.41
     போட
    0.41
     Drying
    0.40
     план
    0.39
     Many
    0.39
    ONT
    0.39
    Act Density 0.004%

    No Known Activations