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

    Neuronpedia

    INDEX
    Explanations

    semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revenge
    -0.07
     mj
    -0.07
    剑
    -0.07
    svm
    -0.06
    qid
    -0.06
    posting
    -0.06
    geo
    -0.06
    _registers
    -0.06
     qualité
    -0.06
    -0.06
    POSITIVE LOGITS
    aşa
    0.06
      ↵
    0.06
    .IContainer
    0.06
    状況
    0.06
    enumerator
    0.06
    _INLINE
    0.06
     '.',
    0.06
                    ↵                ↵
    0.06
    )}>↵
    0.06
     เว
    0.05
    Act Density 0.041%

    No Known Activations