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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৬৫
    0.76
    iah
    0.72
     unintentionally
    0.72
    ვის
    0.70
     deployments
    0.69
     दहा
    0.69
     herni
    0.69
    ensions
    0.68
     mắn
    0.68
     ৬৮
    0.68
    POSITIVE LOGITS
     substitute
    1.04
     substituting
    1.04
    Substitution
    0.99
     substituted
    0.92
     Substitution
    0.92
     substitution
    0.91
     substitutes
    0.90
    substitution
    0.88
     substit
    0.88
    Substitute
    0.87
    Act Density 0.052%

    No Known Activations