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

    Neuronpedia

    INDEX
    Explanations

    unmatched superiority and potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inactive
    0.83
     implicit
    0.80
     helplessness
    0.74
     inactivity
    0.74
     along
    0.74
     smart
    0.72
     Why
    0.71
     abduction
    0.71
     progression
    0.69
    捞
    0.68
    POSITIVE LOGITS
    fortun
    1.13
    fortunately
    1.09
    ipolar
    1.03
    bilical
    1.02
    Fortunately
    0.98
     asemenea
    0.96
    ilateral
    0.94
    expec
    0.92
    uttered
    0.90
    ilever
    0.89
    Act Density 0.065%

    No Known Activations