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

    Neuronpedia

    INDEX
    Explanations

    tight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @[
    -0.07
    avour
    -0.06
     místo
    -0.06
     verschiedene
    -0.06
    acebook
    -0.06
     Kinder
    -0.06
     Influ
    -0.06
    �
    -0.06
    aza
    -0.06
    POL
    -0.06
    POSITIVE LOGITS
     architects
    0.06
    .Value
    0.06
    ‌اند
    0.06
    탈
    0.06
     Lig
    0.06
    _Ent
    0.06
    :Add
    0.06
     protecting
    0.06
    rist
    0.06
    луги
    0.06
    Act Density 0.001%

    No Known Activations