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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nyere
    -0.08
    ogan
    -0.07
    angebote
    -0.07
     Cleaning
    -0.07
    ünde
    -0.07
    andie
    -0.07
    正在
    -0.07
     Verbrauch
    -0.07
    beheer
    -0.07
    gelopen
    -0.07
    POSITIVE LOGITS
     preferences
    0.12
    Specify
    0.11
     personalization
    0.11
    사항
    0.11
    Preferences
    0.11
     Specify
    0.10
     voorkeur
    0.10
     specifications
    0.10
    specified
    0.10
    _constraints
    0.09
    Act Density 0.050%

    No Known Activations