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

    Neuronpedia

    INDEX
    Explanations

    Network connectivity tests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Races
    -0.07
    intent
    -0.06
    =(↵
    -0.06
    lod
    -0.06
    stadt
    -0.06
    icide
    -0.06
     entail
    -0.06
     races
    -0.06
     columns
    -0.06
     deploy
    -0.06
    POSITIVE LOGITS
    .SUCCESS
    0.06
    VRTX
    0.06
     recurs
    0.06
    Cfg
    0.06
    '][$
    0.06
    .TrimSpace
    0.06
     qry
    0.06
     Nic
    0.06
    objc
    0.06
     poměr
    0.06
    Act Density 0.047%

    No Known Activations