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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /action
    -0.08
    county
    -0.07
     initWithTitle
    -0.07
    .authorization
    -0.07
    _head
    -0.07
    小时
    -0.07
    					
↵
    -0.06
    dropout
    -0.06
     Holidays
    -0.06
    _subset
    -0.06
    POSITIVE LOGITS
     perish
    0.06
     Nicolas
    0.06
     νε
    0.06
    스코
    0.06
    issenschaft
    0.06
     поддерж
    0.06
    Ger
    0.05
    Für
    0.05
     wear
    0.05
     MAKE
    0.05
    Act Density 0.000%

    No Known Activations