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

    Neuronpedia

    INDEX
    Explanations

    you are needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     className
    0.29
     நாம்
    0.28
     encapsulation
    0.28
     Мо
    0.28
    قي
    0.28
    ানো
    0.26
     మనం
    0.26
    0.26
     ছিল
    0.26
    Segmentation
    0.26
    POSITIVE LOGITS
     want
    0.46
     know
    0.40
     wanna
    0.36
    want
    0.35
     prefer
    0.34
     need
    0.34
     suspect
    0.33
     think
    0.32
     gotta
    0.31
     KNOW
    0.30
    Act Density 0.146%

    No Known Activations