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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    energy
    -0.07
     sine
    -0.07
     servo
    -0.07
    奴
    -0.07
     zb
    -0.07
     Rico
    -0.07
    _Execute
    -0.06
    _tt
    -0.06
     Респуб
    -0.06
     revenue
    -0.06
    POSITIVE LOGITS
    pick
    0.08
    JAVA
    0.08
    AKER
    0.07
    верх
    0.07
    Ю
    0.07
    şehir
    0.07
    أفكار
    0.07
    夸大
    0.07
    榭
    0.06
    boxed
    0.06
    Act Density 0.014%

    No Known Activations