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

    Neuronpedia

    INDEX
    Explanations

    brainstorming lists, identifying specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     synchronization
    0.46
     shipments
    0.42
     deformations
    0.41
     tetrachloride
    0.41
     hidro
    0.40
     geometries
    0.40
     sublicense
    0.40
     symb
    0.39
     demonstrated
    0.38
     encryption
    0.38
    POSITIVE LOGITS
     list
    0.93
     lijst
    0.91
     lists
    0.89
    リスト
    0.89
     brainstorm
    0.87
     لیست
    0.86
     liste
    0.85
     списка
    0.85
     lista
    0.84
     brainstorming
    0.84
    Act Density 0.045%

    No Known Activations