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

    Neuronpedia

    INDEX
    Explanations

    blog posts / conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	left
    -0.06
    speaker
    -0.06
    IH
    -0.06
     insurers
    -0.06
    PN
    -0.06
     rushed
    -0.06
     Pe
    -0.06
     monitored
    -0.06
    DG
    -0.06
    Normalization
    -0.06
    POSITIVE LOGITS
    .effects
    0.07
    (['/
    0.07
     UnityEngine
    0.07
    xr
    0.06
    ([],
    0.06
     circa
    0.06
    enedor
    0.06
     Excellence
    0.06
    .deleteById
    0.06
    ANCE
    0.06
    Act Density 0.070%

    No Known Activations