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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ang
    0.29
    ae
    0.28
    bere
    0.28
    hydrox
    0.28
    chem
    0.27
    grain
    0.27
    gang
    0.27
    repent
    0.27
    rauen
    0.27
    engel
    0.27
    POSITIVE LOGITS
    ('
    0.34
    ("$
    0.30
    ("
    0.30
     previewBuilder
    0.30
    位于
    0.29
     bogus
    0.28
     className
    0.28
     新
    0.28
     来
    0.27
            
    0.27
    Act Density 1.007%

    No Known Activations