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

    Neuronpedia

    INDEX
    Explanations

    correctness and common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Presiden
    0.74
     surfaces
    0.74
    omega
    0.71
    russ
    0.70
     President
    0.68
    owaniu
    0.67
    хь
    0.67
     threat
    0.65
    ishops
    0.65
     Threats
    0.64
    POSITIVE LOGITS
     rectify
    0.94
     정확
    0.87
    download
    0.85
    correct
    0.84
    incorrect
    0.82
    baiki
    0.81
    Correct
    0.81
    donate
    0.80
     inaccurate
    0.80
     Tjiwarl
    0.78
    Act Density 0.002%

    No Known Activations