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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Extras
    -0.08
    ちょ
    -0.07
    ='<?
    -0.07
     Debt
    -0.07
    )",↵
    -0.06
     Shanghai
    -0.06
    _Ptr
    -0.06
     Basin
    -0.06
    _nodes
    -0.06
    Unchecked
    -0.06
    POSITIVE LOGITS
     περι
    0.06
    지도
    0.06
    allocated
    0.06
     serialization
    0.06
     veřejné
    0.06
     Erd
    0.05
     Daten
    0.05
    Break
    0.05
    .Lookup
    0.05
     робот
    0.05
    Act Density 0.009%

    No Known Activations