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

    Neuronpedia

    INDEX
    Explanations

    astro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.72
    InjectAttribute
    -0.64
    BeginContext
    -0.61
    Filmografia
    -0.60
    CreateModel
    -0.59
    fjspx
    -0.59
     defaultstate
    -0.55
    IsContent
    -0.52
    Bronnen
    -0.52
    EndContext
    -0.52
    POSITIVE LOGITS
     fermés
    0.55
     particulières
    0.47
     culturelles
    0.47
    DP
    0.47
    ML
    0.47
     découver
    0.47
     Leve
    0.46
    wel
    0.45
     définiti
    0.45
    nthetic
    0.45
    Act Density 0.000%

    No Known Activations