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

    Neuronpedia

    INDEX
    Explanations

    chemical formulas and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
                      
    0.41
    Click
    0.40
     মিথ
    0.37
     ساع
    0.37
     કામ
    0.37
                  
    0.37
    Confirm
    0.37
     શકાય
    0.37
    Lower
    0.37
    ={
    0.36
    POSITIVE LOGITS
     musicals
    0.42
    ネックレス
    0.40
     PRINC
    0.38
    Ě
    0.38
    िर
    0.38
     umbrella
    0.36
    SKA
    0.36
    ploidy
    0.36
     crew
    0.35
    ोले
    0.35
    Act Density 0.001%

    No Known Activations