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

    Neuronpedia

    INDEX
    Explanations

    mechanism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apart
    -0.07
     Based
    -0.07
    Wonder
    -0.07
     proud
    -0.07
    Thông
    -0.06
    anto
    -0.06
    ATO
    -0.06
    Apart
    -0.06
    bad
    -0.06
    uration
    -0.06
    POSITIVE LOGITS
    kenin
    0.06
    NSObject
    0.06
    precision
    0.06
    ,ev
    0.06
     herkes
    0.06
    were
    0.06
     Symfony
    0.06
    ContextHolder
    0.06
    enums
    0.06
     stunned
    0.06
    Act Density 0.090%

    No Known Activations