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

    Neuronpedia

    INDEX
    Explanations

    Planning text generation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     السيد
    -0.08
    .Rad
    -0.08
     Independence
    -0.08
     Warning
    -0.08
     Indep
    -0.08
     SOS
    -0.08
     Comercial
    -0.08
     Dolores
    -0.08
     Independ
    -0.08
     ditch
    -0.08
    POSITIVE LOGITS
     helps
    0.09
     поможет
    0.09
     help
    0.08
     hopefully
    0.08
     mak
    0.08
     tick
    0.08
    обходимо
    0.08
     essence
    0.08
     consent
    0.07
    Sure
    0.07
    Act Density 0.054%

    No Known Activations