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

    Neuronpedia

    INDEX
    Explanations

    immigration and criminals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ress
    -0.06
     Mesh
    -0.06
    Days
    -0.06
    �
    -0.06
     Том
    -0.06
    rea
    -0.06
    .Toolkit
    -0.06
    EMU
    -0.06
     lleg
    -0.06
     Shut
    -0.06
    POSITIVE LOGITS
     inexp
    0.06
     foundational
    0.06
    getMessage
    0.06
     pubb
    0.06
     Fiat
    0.06
     enrol
    0.06
    γκο
    0.06
        ↵↵
    0.06
     Fires
    0.06
    $core
    0.06
    Act Density 0.004%

    No Known Activations