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

    Neuronpedia

    INDEX
    Explanations

    anger management, surprisingly specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ContentView
    0.42
     balo
    0.40
    Reducing
    0.40
    揉
    0.39
     PublicKey
    0.38
     enf
    0.38
    ഘ
    0.38
    Breaking
    0.37
    Grouping
    0.37
    publicKey
    0.37
    POSITIVE LOGITS
     researched
    0.43
     request
    0.42
     S
    0.41
     diversos
    0.41
     libertad
    0.39
     siempre
    0.39
     সবসময়
    0.38
     requested
    0.38
    pati
    0.38
    orse
    0.38
    Act Density 0.000%

    No Known Activations