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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Control
    -0.07
     Facility
    -0.07
    _Format
    -0.07
    BUILD
    -0.07
    StateMachine
    -0.07
     overwrite
    -0.07
     SUMMARY
    -0.06
     처
    -0.06
    rogate
    -0.06
    	write
    -0.06
    POSITIVE LOGITS
     Jess
    0.08
    (w
    0.06
    [k
    0.06
     [{'
    0.06
    (O
    0.06
     #[
    0.06
    Jess
    0.06
    něte
    0.06
     kích
    0.06
     worlds
    0.06
    Act Density 0.016%

    No Known Activations