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

    Neuronpedia

    INDEX
    Explanations

    software components and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allelujah
    0.47
    erval
    0.42
    atterson
    0.41
     положи
    0.41
     overpower
    0.41
     overpowering
    0.41
     Moines
    0.41
    プーン
    0.40
     positiva
    0.40
     cheering
    0.40
    POSITIVE LOGITS
    组件
    0.55
     services
    0.54
     composants
    0.54
     Extensions
    0.52
     Services
    0.51
    Services
    0.50
     modules
    0.50
    服务
    0.50
     servizi
    0.50
    Module
    0.49
    Act Density 0.050%

    No Known Activations