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

    Neuronpedia

    INDEX
    Explanations

    editor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wich
    -0.08
    .mesh
    -0.08
     Rosie
    -0.07
    🏵
    -0.07
    uble
    -0.07
    raith
    -0.07
     River
    -0.07
     Fulton
    -0.07
    burgh
    -0.07
    bine
    -0.07
    POSITIVE LOGITS
     교
    0.08
    \models
    0.07
     kap
    0.07
    (factor
    0.07
     editors
    0.07
    냈
    0.07
     acompaña
    0.06
    打进
    0.06
     task
    0.06
     الاقتصادي
    0.06
    Act Density 0.009%

    No Known Activations