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

    Neuronpedia

    INDEX
    Explanations

    trials of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reports
    0.86
     Report
    0.81
     reports
    0.73
     Reporting
    0.71
     report
    0.71
     foresee
    0.70
    Reports
    0.67
     present
    0.67
     making
    0.67
     berichten
    0.66
    POSITIVE LOGITS
    ItemBackground
    0.78
    𝘫
    0.78
    EndOf
    0.78
     //</
    0.75
    𝚓
    0.74
    𝟘
    0.73
     വിവര
    0.73
    →</
    0.73
    rodní
    0.71
    ന്തര
    0.71
    Act Density 0.006%

    No Known Activations