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
     khá
    -0.07
     Fade
    -0.07
    ωμάτιο
    -0.07
     verschied
    -0.07
     điển
    -0.07
     بالا
    -0.07
     denně
    -0.07
    /gpio
    -0.07
    ae
    -0.07
    avia
    -0.07
    POSITIVE LOGITS
     trust
    0.17
     Trust
    0.16
    Trust
    0.14
    trust
    0.13
     trusts
    0.11
     trusting
    0.10
     trustworthy
    0.10
     trusted
    0.09
     entrusted
    0.09
     Trusted
    0.08
    Act Density 0.013%

    No Known Activations