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

    Neuronpedia

    INDEX
    Explanations

    trust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ofere
    -0.07
     cạnh
    -0.06
    锦
    -0.06
     Gör
    -0.06
     الأم
    -0.06
    .radians
    -0.06
    Markers
    -0.06
     superficial
    -0.06
     paved
    -0.06
     pré
    -0.06
    POSITIVE LOGITS
     trust
    0.13
     Trust
    0.11
    Trust
    0.10
     trusts
    0.08
    .Sh
    0.08
    _DT
    0.07
    GN
    0.07
    ΕΣ
    0.07
    .v
    0.07
    -st
    0.07
    Act Density 0.013%

    No Known Activations