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

    Neuronpedia

    INDEX
    Explanations

    inclusion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )-
    -0.06
     pravděpodob
    -0.06
    Reduce
    -0.06
     Tiger
    -0.06
    shelf
    -0.06
     �
    -0.06
     Sass
    -0.06
    timestamp
    -0.05
     Kimber
    -0.05
    -equiv
    -0.05
    POSITIVE LOGITS
    .deg
    0.07
     hostage
    0.07
     genitals
    0.07
     Funding
    0.07
     (£
    0.07
     across
    0.07
    agues
    0.07
     counting
    0.06
     ducks
    0.06
     όπως
    0.06
    Act Density 0.003%

    No Known Activations