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

    Neuronpedia

    INDEX
    Explanations

    word components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mit
    0.52
     Mit
    0.43
    mit
    0.42
     Deity
    0.42
     kas
    0.40
     gestalt
    0.39
     Healing
    0.38
    Mit
    0.37
    তান
    0.37
     Content
    0.36
    POSITIVE LOGITS
    utes
    0.55
    UTES
    0.44
    udes
    0.42
     ут
    0.42
    üs
    0.40
     utt
    0.38
    सित
    0.38
    üd
    0.37
     everywhere
    0.37
    UTE
    0.36
    Act Density 0.000%

    No Known Activations