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

    Neuronpedia

    INDEX
    Explanations

    names and pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Projection
    -0.07
     �
    -0.07
     本
    -0.06
    894
    -0.06
    Targets
    -0.06
    ,V
    -0.06
    اظ
    -0.06
     protested
    -0.06
    Product
    -0.06
    _w
    -0.06
    POSITIVE LOGITS
    ительность
    0.07
     responseData
    0.07
    both
    0.06
    اعر
    0.06
    (bucket
    0.06
     try
    0.06
     möglich
    0.06
    .lng
    0.06
    ερμαν
    0.06
    rowse
    0.06
    Act Density 0.034%

    No Known Activations