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

    Neuronpedia

    INDEX
    Explanations

    validation and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     麻
    0.77
     Glas
    0.76
    واد
    0.74
     secretions
    0.74
     soldered
    0.71
     compartments
    0.70
     EIS
    0.69
     multitasking
    0.69
     condolences
    0.68
     developments
    0.66
    POSITIVE LOGITS
     validator
    1.87
     validators
    1.84
     validation
    1.81
     Validation
    1.81
    Validation
    1.80
    validator
    1.79
     Validate
    1.75
    Validator
    1.75
     validations
    1.73
    Validate
    1.73
    Act Density 0.259%

    No Known Activations