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

    Neuronpedia

    INDEX
    Explanations

    memory management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    statistic
    1.50
    ungg
    1.42
     Encyclopaedia
    1.41
    mata
    1.40
     Organisation
    1.36
     explains
    1.34
     (£
    1.33
     prawns
    1.30
    did
    1.30
    éraire
    1.28
    POSITIVE LOGITS
     sense
    2.43
     nuis
    2.34
     passable
    2.32
     그런
    2.29
     приблизи
    2.18
    wesen
    2.17
     uninhab
    2.17
     distinguishable
    2.14
     sure
    2.14
    7
    2.13
    Act Density 0.238%

    No Known Activations