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

    Neuronpedia

    INDEX
    Explanations

    birthdates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accounts
    -0.07
    Batman
    -0.06
    eten
    -0.06
    واهد
    -0.06
     eliminate
    -0.06
    ocabulary
    -0.06
     розмі
    -0.06
     Arrival
    -0.06
     Rock
    -0.06
    .Server
    -0.06
    POSITIVE LOGITS
     Undert
    0.07
     Kro
    0.07
    84
    0.07
     соци
    0.07
    KindOfClass
    0.07
    81
    0.06
    veriş
    0.06
     ошиб
    0.06
    为空
    0.06
     selfish
    0.06
    Act Density 0.004%

    No Known Activations