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

    Neuronpedia

    INDEX
    Explanations

    severity and related categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     despatch
    0.42
     hexane
    0.40
    ρίας
    0.40
    లన
    0.40
     MacDonald
    0.39
     virial
    0.39
     cyclohexane
    0.38
    Dropped
    0.37
    룹
    0.37
     analogues
    0.37
    POSITIVE LOGITS
    severity
    0.48
                                  
    0.47
      
    0.45
          
    0.44
    Severity
    0.43
    feeding
    0.43
    Categor
    0.43
              
    0.42
     severity
    0.42
                      
    0.41
    Act Density 0.000%

    No Known Activations