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

    Neuronpedia

    INDEX
    Explanations

    current DID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rän
    0.46
    ਡ
    0.45
    say
    0.44
    ਿ
    0.43
    ec
    0.42
    ears
    0.41
     бе
    0.41
    රු
    0.41
     ਪ
    0.41
     музея
    0.41
    POSITIVE LOGITS
     Mana
    0.40
     Type
    0.39
     Conflict
    0.39
     Gestion
    0.39
     mana
    0.38
     Conflicts
    0.38
     Auth
    0.37
    formatter
    0.37
     Horm
    0.37
    Formatter
    0.37
    Act Density 0.004%

    No Known Activations