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

    Neuronpedia

    INDEX
    Explanations

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pakistan
    -0.06
     Rubber
    -0.06
     smells
    -0.06
     sky
    -0.06
     dao
    -0.06
    .db
    -0.06
    species
    -0.06
    dataset
    -0.06
     childhood
    -0.05
    客户
    -0.05
    POSITIVE LOGITS
     gore
    0.08
    ERGE
    0.07
    _Query
    0.07
    _fmt
    0.07
    ओ
    0.06
    地说
    0.06
    redict
    0.06
     اقدام
    0.06
    _action
    0.06
     reunited
    0.06
    Act Density 0.022%

    No Known Activations