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

    Neuronpedia

    INDEX
    Explanations

    you, "never" or "need"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
                    
    0.19
                           
    0.19
     anaemia
    0.18
     neuritis
    0.18
                        
    0.17
     urination
    0.17
     prohibiting
    0.17
     defamatory
    0.17
     denotes
    0.17
     বৃদ্ধি
    0.17
    POSITIVE LOGITS
     gotta
    0.27
     got
    0.24
     know
    0.24
     really
    0.23
    してる
    0.23
     KNOW
    0.23
     get
    0.22
     kinda
    0.22
     hafta
    0.22
     REALLY
    0.21
    Act Density 0.152%

    No Known Activations