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

    Neuronpedia

    INDEX
    Explanations

    receiving

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastly
    -0.08
    滥
    -0.08
    "){
↵
    -0.08
    Sketch
    -0.07
    laughs
    -0.07
    😂
    -0.07
     dissert
    -0.07
    .CODE
    -0.07
     designers
    -0.07
    🚾
    -0.07
    POSITIVE LOGITS
    .annotations
    0.07
    PAIR
    0.07
     Institute
    0.07
    还包括
    0.07
     Folder
    0.07
    ﯙ
    0.07
     ->
    0.07
    博览会
    0.07
    omal
    0.07
    .BO
    0.07
    Act Density 0.019%

    No Known Activations