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

    Neuronpedia

    INDEX
    Explanations

    validation rules and constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     safegu
    0.45
    odeal
    0.44
    CTk
    0.43
    StoredKeys
    0.42
     endExpNow
    0.42
     کرونا
    0.42
    ijen
    0.41
     sputter
    0.41
    даго
    0.40
    ികളും
    0.40
    POSITIVE LOGITS
     Validation
    0.95
     validator
    0.86
     validation
    0.85
     Validator
    0.82
    Validation
    0.81
     ValidationError
    0.81
    validation
    0.77
    constraints
    0.77
     Constraint
    0.77
     validations
    0.75
    Act Density 0.005%

    No Known Activations