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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imizin
    -0.07
    endet
    -0.07
    .getDescription
    -0.07
    !),
    -0.06
     centuries
    -0.06
     anno
    -0.06
    _code
    -0.06
    칭
    -0.06
    trinsic
    -0.06
    (master
    -0.06
    POSITIVE LOGITS
    icional
    0.07
    .getBounds
    0.07
     RID
    0.07
     Vij
    0.07
     Risk
    0.06
    piry
    0.06
     CSR
    0.06
     risk
    0.06
                                    
    0.06
     statt
    0.06
    Act Density 0.037%

    No Known Activations