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

    Neuronpedia

    INDEX
    Explanations

    discussion or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aeration
    0.50
     aficionados
    0.45
     additives
    0.44
     solder
    0.43
     avion
    0.43
     adhesives
    0.43
     manne
    0.42
     ferry
    0.41
     newsletters
    0.41
     ferries
    0.40
    POSITIVE LOGITS
    0.71
    琀
    0.64
    0.57
    0.57
    昀
    0.53
    0.52
    ฀
    0.48
     ́
    0.48
     ●
    0.47
     -&
    0.47
    Act Density 0.003%

    No Known Activations