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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ơn
    -0.07
    Penn
    -0.07
     Satoshi
    -0.07
    桂林
    -0.07
    沉浸
    -0.07
    民生
    -0.07
     gắn
    -0.06
    所在
    -0.06
     allen
    -0.06
    athan
    -0.06
    POSITIVE LOGITS
    (Operation
    0.08
    AccountId
    0.08
    Star
    0.07
    .emptyList
    0.07
     wizards
    0.07
    Lt
    0.07
    ufacturer
    0.07
    StringBuilder
    0.07
     Теперь
    0.07
     thugs
    0.07
    Act Density 0.004%

    No Known Activations