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

    Neuronpedia

    INDEX
    Explanations

    technical writing snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     здоров
    -0.07
     Tantra
    -0.07
    یری
    -0.07
    альным
    -0.06
     bridge
    -0.06
    ف
    -0.06
    ß
    -0.06
     interchange
    -0.06
    锁
    -0.06
     mulheres
    -0.06
    POSITIVE LOGITS
     whatsapp
    0.07
    Human
    0.07
    msgid
    0.07
     eapply
    0.06
    :Set
    0.06
     musel
    0.06
    ,[
    0.06
     hookup
    0.06
    phy
    0.06
    Contacts
    0.06
    Act Density 0.000%

    No Known Activations