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

    Neuronpedia

    INDEX
    Explanations

    interaction and behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    law
    -0.57
     Law
    -0.54
    Portail
    -0.51
     the
    -0.51
     scheme
    -0.50
    zle
    -0.50
    room
    -0.50
     contact
    -0.50
    ẾT
    -0.49
     law
    -0.49
    POSITIVE LOGITS
     Roskov
    0.75
     nahilalakip
    0.74
    Diwedd
    0.73
    UrlResolution
    0.70
     vPvB
    0.69
    /**
    0.68
     AssemblyTitle
    0.67
    estacks
    0.67
    Према
    0.66
     Réponses
    0.66
    Act Density 0.162%

    No Known Activations