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

    Neuronpedia

    INDEX
    Explanations

    explaining what, why, how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     duvar
    0.28
     hMut
    0.28
     drowsiness
    0.28
     produziert
    0.27
     microtubules
    0.27
     elektromagnet
    0.27
    نڈ
    0.27
     spacer
    0.27
     بیمار
    0.27
     vertebr
    0.26
    POSITIVE LOGITS
     advantages
    0.54
     Advantages
    0.52
     benefits
    0.51
    Advantages
    0.50
     Benefits
    0.50
    advantages
    0.50
     examples
    0.48
     Vorteile
    0.48
     characteristics
    0.47
    Benefits
    0.46
    Act Density 1.347%

    No Known Activations