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

    Neuronpedia

    INDEX
    Explanations

    formal documents and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contracted
    0.75
    justify
    0.72
     liable
    0.71
     contracts
    0.70
     blaming
    0.70
     justify
    0.69
     결과
    0.68
     blame
    0.68
     fault
    0.68
     vox
    0.68
    POSITIVE LOGITS
    Exhibit
    1.00
     exhibits
    0.98
     exhibit
    0.91
     Exhibits
    0.87
     Exhibit
    0.84
     EXHIB
    0.82
     राइड
    0.78
    hesda
    0.77
     recital
    0.75
     heading
    0.75
    Act Density 0.099%

    No Known Activations