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

    Neuronpedia

    INDEX
    Explanations

    resetting to default values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tapered
    0.49
     whispers
    0.48
     EBITDA
    0.48
     sprints
    0.46
     serves
    0.43
     forage
    0.43
     plumes
    0.43
     markets
    0.43
     subtract
    0.43
     sutures
    0.43
    POSITIVE LOGITS
     getDefault
    0.59
    Default
    0.53
    default
    0.50
     default
    0.49
     Default
    0.49
     மீட்ட
    0.48
     умолчанию
    0.45
    Defaults
    0.45
    Template
    0.43
     defaults
    0.43
    Act Density 0.001%

    No Known Activations