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

    Neuronpedia

    INDEX
    Explanations

    descriptive lists, examples, or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    0.98
    A
    0.86
    ↵
    0.85
     l
    0.80
    D
    0.77
       
    0.75
    }\
    0.74
      
    0.73
                    
    0.73
    F
    0.73
    POSITIVE LOGITS
     פון
    0.90
     tentativas
    0.90
     среды
    0.86
    popupIsOpen
    0.86
     счастли
    0.84
    टेगरी
    0.84
     carreteras
    0.83
     alternativas
    0.83
     děti
    0.82
     nutrientes
    0.81
    Act Density 0.001%

    No Known Activations