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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uçak
    -0.07
     core
    -0.07
     �
    -0.06
    inte
    -0.06
     sine
    -0.06
     around
    -0.06
    sing
    -0.06
    inox
    -0.06
     AUX
    -0.06
    aze
    -0.06
    POSITIVE LOGITS
     methods
    0.17
     method
    0.16
     Method
    0.14
     Methods
    0.14
    method
    0.13
    Method
    0.12
    methods
    0.11
    METHOD
    0.11
    Methods
    0.11
     methodology
    0.10
    Act Density 0.069%

    No Known Activations