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

    Neuronpedia

    INDEX
    Explanations

    reports and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    instagram
    0.83
    Teach
    0.82
     OpenGL
    0.81
    antics
    0.79
    ebly
    0.78
     OpenCV
    0.78
    musik
    0.77
     felicidad
    0.76
     instagram
    0.76
    uretics
    0.75
    POSITIVE LOGITS
     report
    2.54
     recommendations
    2.42
     findings
    2.39
     Report
    2.35
     conclusions
    2.34
     Findings
    2.26
     Recommendations
    2.18
    Recommendations
    2.10
    Findings
    2.08
     recommendation
    2.04
    Act Density 0.297%

    No Known Activations