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

    Neuronpedia

    INDEX
    Explanations

    accounting, CPA

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endment
    -0.06
    _case
    -0.06
    DIFF
    -0.06
    aska
    -0.06
    endforeach
    -0.06
    327
    -0.06
    地址
    -0.06
     Negative
    -0.06
     gaps
    -0.06
    ihn
    -0.06
    POSITIVE LOGITS
     costing
    0.07
    	ev
    0.06
    _FACTOR
    0.06
    <V
    0.06
     totals
    0.06
    	login
    0.06
     russ
    0.06
     steals
    0.06
     Peg
    0.06
     config
    0.06
    Act Density 0.015%

    No Known Activations