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

    Neuronpedia

    INDEX
    Explanations

    experimental setups and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personnalité
    0.96
     мнение
    0.94
    Hobbies
    0.93
     فهم
    0.93
     fiabilité
    0.92
    Ticket
    0.91
     personalità
    0.89
    成就
    0.89
     зарабаты
    0.89
    ḵ
    0.88
    POSITIVE LOGITS
     experiment
    1.73
     experiments
    1.68
     stimulation
    1.61
     stimuli
    1.60
     experimental
    1.56
     실험
    1.53
     experimentally
    1.49
     Experiment
    1.48
     Experiments
    1.48
     treatments
    1.47
    Act Density 0.444%

    No Known Activations