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

    Neuronpedia

    INDEX
    Explanations

    Data types

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legitimacy
    -0.10
     visitation
    -0.08
     wellbeing
    -0.08
     efficacy
    -0.08
     turnover
    -0.08
     legislation
    -0.08
     Exit
    -0.08
     SWOT
    -0.08
     interventions
    -0.08
    êtes
    -0.08
    POSITIVE LOGITS
    scaled
    0.08
    _precision
    0.08
    _integer
    0.08
     scherpe
    0.08
     банков
    0.08
     scherp
    0.08
     기본
    0.08
     minted
    0.08
     bih
    0.08
    picture
    0.08
    Act Density 0.006%

    No Known Activations