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

    Neuronpedia

    INDEX
    Explanations

    debates about regulations or issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geometrical
    0.47
     visionary
    0.41
     predefined
    0.40
     iterating
    0.39
     geological
    0.38
     linear
    0.38
     analytical
    0.38
     hier
    0.37
     reference
    0.37
     team
    0.36
    POSITIVE LOGITS
     fentanyl
    0.95
     fracking
    0.95
     ransomware
    0.91
     opioids
    0.91
     vaping
    0.86
     PFAS
    0.82
     Brexit
    0.81
     pesticides
    0.80
     opioid
    0.79
     glyphosate
    0.77
    Act Density 0.026%

    No Known Activations