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

    Neuronpedia

    INDEX
    Explanations

    trusted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trusted
    -1.40
     trust
    -1.28
    trust
    -1.24
     trusting
    -1.22
    Trust
    -1.21
     Trust
    -1.19
    trusted
    -1.15
     TRUST
    -1.07
     trusts
    -1.01
     Trusted
    -1.01
    POSITIVE LOGITS
    expandindo
    0.69
    jface
    0.54
    Complete
    0.51
     Complete
    0.50
    getSystemService
    0.48
    ),),
    0.47
    Heraus
    0.47
    uyler
    0.45
    Pru
    0.45
    iele
    0.44
    Act Density 0.058%

    No Known Activations