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

    Neuronpedia

    INDEX
    Explanations

    greeting followed by titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creators
    0.83
     apex
    0.83
     dachshund
    0.78
     makers
    0.77
     developers
    0.77
     Python
    0.76
     Chernobyl
    0.76
     compilers
    0.75
     borrowers
    0.75
     system
    0.74
    POSITIVE LOGITS
    Professor
    1.91
     Professor
    1.87
    Dr
    1.79
    Lieutenant
    1.76
    Colonel
    1.75
     Lieutenant
    1.74
     Councillor
    1.73
    Captain
    1.71
     Lieut
    1.68
     Dr
    1.66
    Act Density 0.086%

    No Known Activations