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

    Neuronpedia

    INDEX
    Explanations

    c-suite executives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rigs
    0.44
     rigging
    0.44
    ક્ત
    0.40
     rig
    0.40
    αλ
    0.39
    нул
    0.38
    magnitude
    0.38
     rigged
    0.37
     Riggs
    0.36
    거
    0.36
    POSITIVE LOGITS
     suite
    0.84
    Suite
    0.82
     Suite
    0.79
    suite
    0.74
     suites
    0.64
     Suites
    0.46
    سو
    0.44
    uite
    0.44
     सूट
    0.43
     exec
    0.42
    Act Density 0.004%

    No Known Activations