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

    Neuronpedia

    INDEX
    Explanations

    types of places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multifaceted
    0.72
    çando
    0.71
    anguard
    0.71
     multimodal
    0.63
    ful
    0.60
     мүм
    0.60
    çamento
    0.59
    dagog
    0.59
    leukin
    0.59
    çar
    0.59
    POSITIVE LOGITS
     Type
    1.02
     Place
    0.90
     TYPE
    0.90
     exe
    0.88
     给
    0.85
    干燥
    0.85
     PLACE
    0.84
     Activity
    0.84
    収録
    0.84
     place
    0.83
    Act Density 0.000%

    No Known Activations