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

    Neuronpedia

    INDEX
    Explanations

    legal hearings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     villain
    -0.07
    .lastname
    -0.07
     считается
    -0.06
     Whale
    -0.06
    ामक
    -0.06
    wood
    -0.06
    قد
    -0.06
    Traversal
    -0.06
     Sierra
    -0.06
     Alo
    -0.06
    POSITIVE LOGITS
    ROL
    0.07
    Hom
    0.07
    .remote
    0.07
     reset
    0.06
     nấu
    0.06
    mutations
    0.06
     penis
    0.06
    分享
    0.06
     QU
    0.06
     BED
    0.06
    Act Density 0.017%

    No Known Activations