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

    Neuronpedia

    INDEX
    Explanations

    so introducing explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zyg
    0.36
     gastronomic
    0.36
     svm
    0.35
     thyroid
    0.33
     inorder
    0.33
     organs
    0.33
     makeshift
    0.33
     trav
    0.33
     thio
    0.32
     postural
    0.32
    POSITIVE LOGITS
    an
    0.37
    all
    0.36
     получите
    0.36
    totally
    0.35
    everything
    0.35
     didn
    0.35
     plenty
    0.35
     जुड़े
    0.34
     있고
    0.34
     admittedly
    0.34
    Act Density 0.019%

    No Known Activations