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

    Neuronpedia

    INDEX
    Explanations

    inadvertently signs, Indicator Tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     стимули
    0.40
                                  
    0.40
     stimulates
    0.39
     flexing
    0.39
     rotates
    0.39
     glavni
    0.39
     Guidelines
    0.38
     Tolerance
    0.38
                                 
    0.37
    ড়িয়ে
    0.37
    POSITIVE LOGITS
    嫂
    0.39
    รร
    0.38
     बहू
    0.37
    צוני
    0.37
     northwest
    0.36
     oversized
    0.35
     Northwest
    0.35
    шк
    0.35
     rapidly
    0.35
    ,]$
    0.35
    Act Density 0.008%

    No Known Activations