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

    Neuronpedia

    INDEX
    Explanations

    Representatives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    paring
    -0.06
    前
    -0.06
    rored
    -0.06
     )]↵
    -0.06
     costly
    -0.06
     Eh
    -0.06
     Choice
    -0.06
    _KEY
    -0.06
     nelle
    -0.06
    .'''↵
    -0.06
    POSITIVE LOGITS
    优势
    0.07
    	internal
    0.07
    ,UnityEngine
    0.07
     CharSequence
    0.06
     کال
    0.06
    ी.
    0.06
     vlády
    0.06
     آمریک
    0.06
     authoritarian
    0.06
     crimson
    0.06
    Act Density 0.008%

    No Known Activations