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

    Neuronpedia

    INDEX
    Explanations

    Data and record keeping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expect
    -0.06
     practically
    -0.06
     startup
    -0.06
    男性
    -0.06
    oris
    -0.06
    ∧
    -0.06
    itizen
    -0.06
    iming
    -0.06
     aure
    -0.06
     Basis
    -0.06
    POSITIVE LOGITS
    CppObject
    0.07
     tamil
    0.07
    IsRequired
    0.06
    ่องเท
    0.06
     kas
    0.06
    είτε
    0.06
     programmes
    0.06
    جل
    0.06
    ')"↵
    0.06
     createSelector
    0.06
    Act Density 0.111%

    No Known Activations