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

    Neuronpedia

    INDEX
    Explanations

    file paths and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vielfält
    0.40
    Neb
    0.37
     अचार
    0.37
    Diverse
    0.37
     उत्सा
    0.36
     økonom
    0.36
    Horn
    0.35
    TODO
    0.35
    竿
    0.35
    гра
    0.34
    POSITIVE LOGITS
     yine
    0.39
    的前提
    0.39
     რომელიც
    0.37
     mely
    0.36
     acestea
    0.34
     რომლებიც
    0.34
    しかも
    0.34
     belong
    0.33
    iso
    0.33
     яких
    0.33
    Act Density 0.163%

    No Known Activations