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

    Neuronpedia

    INDEX
    Explanations

    employment/firing/involuntary psychiatric commitment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MY
    -0.07
     Instructions
    -0.07
    	with
    -0.07
     Expand
    -0.06
    _SEC
    -0.06
    -device
    -0.06
    _WRAP
    -0.06
    886
    -0.06
    _fragment
    -0.06
    asu
    -0.06
    POSITIVE LOGITS
    стве
    0.06
    ~/
    0.06
    ωμά
    0.06
    さらに
    0.06
    कन
    0.06
     六
    0.06
    abbit
    0.06
    leground
    0.06
     квар
    0.06
    acted
    0.06
    Act Density 0.229%

    No Known Activations