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

    Neuronpedia

    INDEX
    Explanations

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncovered
    -0.08
     deserve
    -0.07
     silky
    -0.07
     Welch
    -0.07
     lihtsalt
    -0.07
     dictator
    -0.07
     Secrets
    -0.07
    ecard
    -0.07
     silhouette
    -0.07
    wach
    -0.07
    POSITIVE LOGITS
     أنك
    0.08
     tensorflow
    0.08
    Linda
    0.08
    ご了承ください
    0.08
    ظم
    0.08
    .group
    0.08
     installations
    0.08
     Indy
    0.08
    र्द
    0.07
     Assuming
    0.07
    Act Density 0.015%

    No Known Activations