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

    Neuronpedia

    INDEX
    Explanations

    "What is" or "What's" questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contributed
    0.49
     influenced
    0.48
     contributes
    0.47
    Ы
    0.45
     distinguishes
    0.45
     elevates
    0.44
     constitutes
    0.44
     the
    0.43
     differentiates
    0.43
     complicates
    0.42
    POSITIVE LOGITS
     Stakes
    0.43
    धीरे
    0.42
     Wählen
    0.41
     Germans
    0.41
     nouă
    0.40
     indef
    0.39
     बंधन
    0.39
     scegliere
    0.39
     escoger
    0.39
    別人
    0.39
    Act Density 0.006%

    No Known Activations